Ralf Schlüter

Rohit Prabhavalkar, Takaaki Hori, Tara N. Sainath et al.

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of this transition, a number of all-neural ASR architectures were introduced. These so-called end-to-end (E2E) models provide highly integrated, completely neural ASR models, which rely strongly on general machine learning knowledge, learn more consistently from data, while depending less on ASR domain-specific experience. The success and enthusiastic adoption of deep learning accompanied by more generic model architectures lead to E2E models now becoming the prominent ASR approach. The goal of this survey is to provide a taxonomy of E2E ASR models and corresponding improvements, and to discuss their properties and their relation to the classical hidden Markov model (HMM) based ASR architecture. All relevant aspects of E2E ASR are covered in this work: modeling, training, decoding, and external language model integration, accompanied by discussions of performance and deployment opportunities, as well as an outlook into potential future developments.

Wei Zhou, Wilfried Michel, Ralf Schlüter et al.

As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated neural network models of growing size and increasing training epochs. While strong computation resources seem to be the prerequisite of training superior models, we try to overcome it by carefully designing a more efficient training pipeline. In this work, we propose an efficient 3-stage progressive training pipeline to build highly-performing neural transducer models from scratch with very limited computation resources in a reasonable short time period. The effectiveness of each stage is experimentally verified on both Librispeech and Switchboard corpora. The proposed pipeline is able to train transducer models approaching state-of-the-art performance with a single GPU in just 2-3 weeks. Our best conformer transducer achieves 4.1% WER on Librispeech test-other with only 35 epochs of training.

Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher et al.

Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based on feature-space approaches for a conformer-based acoustic model (AM) on the Switchboard 300h dataset. We propose a method, called Weighted-Simple-Add, which adds weighted speaker information vectors to the input of the multi-head self-attention module of the conformer AM. Using this method for SAT, we achieve 3.5% and 4.5% relative improvement in terms of WER on the CallHome part of Hub5'00 and Hub5'01 respectively. Moreover, we build on top of our previous work where we proposed a novel and competitive training recipe for a conformer-based hybrid AM. We extend and improve this recipe where we achieve 11% relative improvement in terms of word-error-rate (WER) on Switchboard 300h Hub5'00 dataset. We also make this recipe efficient by reducing the total number of parameters by 34% relative.

Albert Zeyer, Robin Schmitt, Wei Zhou et al.

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming. We directly compare global-attention and different segmental-attention modeling variants. We develop and compare two separate time-synchronous decoders, one specifically taking the segmental nature into account, yielding further improvements. Using time-synchronous decoding for segmental models is novel and a step towards streaming applications. Our experiments show the importance of a length model to predict the segment boundaries. The final best segmental-attention model using segmental decoding performs better than global-attention, in contrast to other monotonic attention approaches in the literature. Further, we observe that the segmental model generalizes much better to long sequences of up to several minutes.

Wei Zhou, Haotian Wu, Jingjing Xu et al.

ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In this work, we study how to best apply these two opposite objectives with speaker labels to improve conformer-based ASR. We also propose a novel adaptive gradient reversal layer for stable and effective adversarial training without tuning effort. Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training. We also explore their combination for further improvement, achieving the same performance as i-vectors plus adversarial training. Our best speaker-based MTL achieves 7\% relative improvement on the Switchboard Hub5'00 set. We also investigate the effect of such speaker-based MTL w.r.t. cleaner dataset and weaker ASR NN.

Peter Vieting, Christoph Lüscher, Julian Dierkes et al.

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of large pre-trained models efficiently and reduce their complexity. In this work, we study a challenging low resource conversational telephony speech corpus from the medical domain in Vietnamese and German. We show the benefits of using unsupervised techniques beyond simple fine-tuning of large pre-trained models, discuss how to adapt them to a practical telephony task including bandwidth transfer and investigate different data conditions for pre-training and fine-tuning. We outperform the project baselines by 22% relative using pretraining techniques. Further gains of 29% can be achieved by refinements of architecture and training and 6% by adding 0.8 h of in-domain adaptation data.

Zijian Yang, Wei Zhou, Ralf Schlüter et al.

Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models, are rarely investigated in RNN-Transducers. In this work, we propose three lattice-free training objectives, namely lattice-free maximum mutual information, lattice-free segment-level minimum Bayes risk, and lattice-free minimum Bayes risk, which are used for the final posterior output of the phoneme-based neural transducer with a limited context dependency. Compared to criteria using N-best lists, lattice-free methods eliminate the decoding step for hypotheses generation during training, which leads to more efficient training. Experimental results show that lattice-free methods gain up to 6.5% relative improvement in word error rate compared to a sequence-level cross-entropy trained model. Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.

Zijian Yang, Wei Zhou, Ralf Schlüter et al.

Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition. In this work, we show that sequence discriminative training has a strong correlation with ILM subtraction from both theoretical and empirical points of view. Theoretically, we derive that the global optimum of maximum mutual information (MMI) training shares a similar formula as ILM subtraction. Empirically, we show that ILM subtraction and sequence discriminative training achieve similar effects across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context. The benefit of ILM subtraction also becomes much smaller after sequence discriminative training. We also provide an in-depth study to show that sequence discriminative training has a minimal effect on the commonly used zero-encoder ILM estimation, but a joint effect on both encoder and prediction + joint network for posterior probability reshaping including both ILM and blank suppression.

Simon Berger, Peter Vieting, Christoph Boeddeker et al.

Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate speakers and recognize each of them with a single-speaker ASR system. End-to-end models process overlapped speech directly in a single, powerful neural network. This work proposes a middle-ground approach that leverages explicit speech separation similarly to the modular approach but also incorporates mixture speech information directly into the ASR module in order to mitigate the propagation of errors made by the speech separator. We also explore a way to exchange cross-speaker context information through a layer that combines information of the individual speakers. Our system is optimized through separate and joint training stages and achieves a relative improvement of 7% in word error rate over a purely modular setup on the SMS-WSJ task.

Christoph Lüscher, Jingjing Xu, Mohammad Zeineldeen et al.

Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated the usage of neural speaker embeddings for an ASR system. In this work, we present our efforts w.r.t integrating neural speaker embeddings into a conformer based hybrid HMM ASR system. For ASR, our improved embedding extraction pipeline in combination with the Weighted-Simple-Add integration method results in x-vector and c-vector reaching on par performance with i-vectors. We further compare and analyze different speaker embeddings. We present our acoustic model improvements obtained by switching from newbob learning rate schedule to one cycle learning schedule resulting in a ~3% relative WER reduction on Switchboard, additionally reducing the overall training time by 17%. By further adding neural speaker embeddings, we gain additional ~3% relative WER improvement on Hub5'00. Our best Conformer-based hybrid ASR system with speaker embeddings achieves 9.0% WER on Hub5'00 and Hub5'01 with training on SWB 300h.

Peter Vieting, Ralf Schlüter, Hermann Ney

Automatic speech recognition (ASR) systems typically use handcrafted feature extraction pipelines. To avoid their inherent information loss and to achieve more consistent modeling from speech to transcribed text, neural raw waveform feature extractors (FEs) are an appealing approach. Also the wav2vec 2.0 model, which has recently gained large popularity, uses a convolutional FE which operates directly on the speech waveform. However, it is not yet studied extensively in the literature. In this work, we study its capability to replace the standard feature extraction methods in a connectionist temporal classification (CTC) ASR model and compare it to an alternative neural FE. We show that both are competitive with traditional FEs on the LibriSpeech benchmark and analyze the effect of the individual components. Furthermore, we analyze the learned filters and show that the most important information for the ASR system is obtained by a set of bandpass filters.

Daniel Mann, Tina Raissi, Wilfried Michel et al.

We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration statistics. We implement a GPU-based forward-backward algorithm that enables the simultaneous training of label and transition probabilities. We investigate recognition results and additionally Viterbi alignments of our models. We find that while the transition model training does not improve recognition performance, it has a positive impact on the alignment quality. The generated alignments are shown to be viable targets in state-of-the-art Viterbi trainings.

Nick Rossenbach, Ralf Schlüter, Sakriani Sakti

The rapid development of neural text-to-speech (TTS) systems enabled its usage in other areas of natural language processing such as automatic speech recognition (ASR) or spoken language translation (SLT). Due to the large number of different TTS architectures and their extensions, selecting which TTS systems to use for synthetic data creation is not an easy task. We use the comparison of five different TTS decoder architectures in the scope of synthetic data generation to show the impact on CTC-based speech recognition training. We compare the recognition results to computable metrics like NISQA MOS and intelligibility, finding that there are no clear relations to the ASR performance. We also observe that for data generation auto-regressive decoding performs better than non-autoregressive decoding, and propose an approach to quantify TTS generalization capabilities.

Christoph Lüscher, Mohammad Zeineldeen, Zijian Yang et al.

Language barriers present a great challenge in our increasingly connected and global world. Especially within the medical domain, e.g. hospital or emergency room, communication difficulties and delays may lead to malpractice and non-optimal patient care. In the HYKIST project, we consider patient-physician communication, more specifically between a German-speaking physician and an Arabic- or Vietnamese-speaking patient. Currently, a doctor can call the Triaphon service to get assistance from an interpreter in order to help facilitate communication. The HYKIST goal is to support the usually non-professional bilingual interpreter with an automatic speech translation system to improve patient care and help overcome language barriers. In this work, we present our ASR system development efforts for this conversational telephone speech translation task in the medical domain for two languages pairs, data collection, various acoustic model architectures and dialect-induced difficulties.

Peter Vieting, Simon Berger, Thilo von Neumann et al.

Many real-life applications of automatic speech recognition (ASR) require processing of overlapped speech. A common method involves first separating the speech into overlap-free streams on which ASR is performed. Recently, TF-GridNet has shown impressive performance in speech separation in real reverberant conditions. Furthermore, a mixture encoder was proposed that leverages the mixed speech to mitigate the effect of separation artifacts. In this work, we extended the mixture encoder from a static two-speaker scenario to a natural meeting context featuring an arbitrary number of speakers and varying degrees of overlap. We further demonstrate its limits by the integration with separators of varying strength including TF-GridNet. Our experiments result in a new state-of-the-art performance on LibriCSS using a single microphone. They show that TF-GridNet largely closes the gap between previous methods and oracle separation independent of mixture encoding. We further investigate the remaining potential for improvement.

Davyd Naveriani, Albert Zeyer, Ralf Schlüter et al.

Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech recognition. Specifically, we introduce a comprehensive guide to incorporating masked diffusion language models (MDLM) and uniform-state diffusion models (USDMs) for rescoring ASR hypotheses. Additionally, we design a new joint-decoding method that combines CTC and USDM by integrating the framewise probability distributions derived from CTC with the labelwise probability distributions computed by USDM at each decoding step, thereby generating new candidates that combine strong language knowledge from USDM and acoustic information from CTC. Our findings reveal that USDM, as well as MDLM, can significantly improve the accuracy of recognized text. We publish all our code and recipes.

Nick Rossenbach, Benedikt Hilmes, Ralf Schlüter

Synthetic data generated by text-to-speech (TTS) systems can be used to improve automatic speech recognition (ASR) systems in low-resource or domain mismatch tasks. It has been shown that TTS-generated outputs still do not have the same qualities as real data. In this work we focus on the temporal structure of synthetic data and its relation to ASR training. By using a novel oracle setup we show how much the degradation of synthetic data quality is influenced by duration modeling in non-autoregressive (NAR) TTS. To get reference phoneme durations we use two common alignment methods, a hidden Markov Gaussian-mixture model (HMM-GMM) aligner and a neural connectionist temporal classification (CTC) aligner. Using a simple algorithm based on random walks we shift phoneme duration distributions of the TTS system closer to real durations, resulting in an improvement of an ASR system using synthetic data in a semi-supervised setting.

Zijian Yang, Jörg Barkoczi, Ralf Schlüter et al.

Unsupervised speech recognition is a task of training a speech recognition model with unpaired data. To determine when and how unsupervised speech recognition can succeed, and how classification error relates to candidate training objectives, we develop a theoretical framework for unsupervised speech recognition grounded in classification error bounds. We introduce two conditions under which unsupervised speech recognition is possible. The necessity of these conditions are also discussed. Under these conditions, we derive a classification error bound for unsupervised speech recognition and validate this bound in simulations. Motivated by this bound, we propose a single-stage sequence-level cross-entropy loss for unsupervised speech recognition.

Zijian Yang, Wei Zhou, Ralf Schlüter et al.

In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers. Both lattice-free and N-best-list approaches are examined. For lattice-free methods with phoneme-level LMs, we propose a method to approximate the context history to employ LMs with full-context dependency. This approximation can be extended to arbitrary context length and enables the usage of word-level LMs in lattice-free methods. Moreover, a systematic comparison is conducted across lattice-free and N-best-list-based methods. Experimental results on Librispeech show that using the word-level LM in training outperforms the phoneme-level LM. Besides, we find that the context size of the LM used for probability computation has a limited effect on performance. Moreover, our results reveal the pivotal importance of the hypothesis space quality in sequence discriminative training.

Khai Le-Duc, David Thulke, Hung-Phong Tran et al.

Spoken Named Entity Recognition (NER) aims to extract named entities from speech and categorise them into types like person, location, organization, etc. In this work, we present VietMed-NER - the first spoken NER dataset in the medical domain. To our knowledge, our Vietnamese real-world dataset is the largest spoken NER dataset in the world regarding the number of entity types, featuring 18 distinct types. Furthermore, we present baseline results using various state-of-the-art pre-trained models: encoder-only and sequence-to-sequence; and conduct quantitative and qualitative error analysis. We found that pre-trained multilingual models generally outperform monolingual models on reference text and ASR output and encoders outperform sequence-to-sequence models in NER tasks. By translating the transcripts, the dataset can also be utilised for text NER in the medical domain in other languages than Vietnamese. All code, data and models are publicly available: https://github.com/leduckhai/MultiMed/tree/master/VietMed-NER.

Kazuki Irie, Albert Zeyer, Ralf Schlüter et al.

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured Transformer models outperform our baseline models based on the shallow stack of LSTM recurrent neural network layers. We carry out experiments on the open-source LibriSpeech 960hr task, for both 200K vocabulary word-level and 10K byte-pair encoding subword-level language modeling. We apply our word-level models to conventional hybrid speech recognition by lattice rescoring, and the subword-level models to attention based encoder-decoder models by shallow fusion. Second, we show that deep Transformer language models do not require positional encoding. The positional encoding is an essential augmentation for the self-attention mechanism which is invariant to sequence ordering. However, in autoregressive setup, as is the case for language modeling, the amount of information increases along the position dimension, which is a positional signal by its own. The analysis of attention weights shows that deep autoregressive self-attention models can automatically make use of such positional information. We find that removing the positional encoding even slightly improves the performance of these models.

Christoph Lüscher, Eugen Beck, Kazuki Irie et al.

We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for the LibriSpeech task. Detailed descriptions of the system development, including model design, pretraining schemes, training schedules, and optimization approaches are provided for both system architectures. Both hybrid DNN/HMM and attention-based systems employ bi-directional LSTMs for acoustic modeling/encoding. For language modeling, we employ both LSTM and Transformer based architectures. All our systems are built using RWTHs open-source toolkits RASR and RETURNN. To the best knowledge of the authors, the results obtained when training on the full LibriSpeech training set, are the best published currently, both for the hybrid DNN/HMM and the attention-based systems. Our single hybrid system even outperforms previous results obtained from combining eight single systems. Our comparison shows that on the LibriSpeech 960h task, the hybrid DNN/HMM system outperforms the attention-based system by 15% relative on the clean and 40% relative on the other test sets in terms of word error rate. Moreover, experiments on a reduced 100h-subset of the LibriSpeech training corpus even show a more pronounced margin between the hybrid DNN/HMM and attention-based architectures.

Albert Zeyer, Tim Posielek, Ralf Schlüter et al.

This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We provide a comprehensive comparison of techniques to integrate text-only data, including modality matching and dynamic downsampling to reach text-level representations within the encoder. Our experiments on the LibriSpeech corpus show that a larger encoder with a smaller decoder can equal or surpass the performance of architectures with larger decoders. We demonstrate that simple configurations, such as random duration models, are often more effective than complex alternatives, significantly simplifying the training pipeline. All code and recipes are made publicly available.

Peter Vieting, Maximilian Kannen, Benedikt Hilmes et al.

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often falls short compared to classical methods, which we show is largely due to their increased susceptibility to overfitting. This work therefore investigates regularization methods for training ASR models with learnable feature extraction front-ends. First, we examine audio perturbation methods and show that larger relative improvements can be obtained for learnable features. Additionally, we identify two limitations in the standard use of SpecAugment for these front-ends and propose masking in the short time Fourier transform (STFT)-domain as a simple but effective modification to address these challenges. Finally, integrating both regularization approaches effectively closes the performance gap between traditional and learnable features.

Jingjing Xu, Eugen Beck, Zijian Yang et al.

ASR systems are deployed across diverse environments, each with specific hardware constraints. We use supernet training to jointly train multiple encoders of varying sizes, enabling dynamic model size adjustment to fit hardware constraints without redundant training. Moreover, we introduce a novel method called OrthoSoftmax, which applies multiple orthogonal softmax functions to efficiently identify optimal subnets within the supernet, avoiding resource-intensive search. This approach also enables more flexible and precise subnet selection by allowing selection based on various criteria and levels of granularity. Our results with CTC on Librispeech and TED-LIUM-v2 show that FLOPs-aware component-wise selection achieves the best overall performance. With the same number of training updates from one single job, WERs for all model sizes are comparable to or slightly better than those of individually trained models. Furthermore, we analyze patterns in the selected components and reveal interesting insights.

Nick Rossenbach, Robin Schmitt, Tina Raissi et al.

The recently published Loquacious dataset aims to be a replacement for established English automatic speech recognition (ASR) datasets such as LibriSpeech or TED-Lium. The main goal of the Loquacious dataset is to provide properly defined training and test partitions across many acoustic and language domains, with an open license suitable for both academia and industry. To further promote the benchmarking and usability of this new dataset, we present additional resources in the form of n-gram language models (LMs), a grapheme-to-phoneme (G2P) model and pronunciation lexica, with open and public access. Utilizing those additional resources we show experimental results across a wide range of ASR architectures with different label units and topologies. Our initial experimental results indicate that the Loquacious dataset offers a valuable study case for a variety of common challenges in ASR.

Peter Vieting, Simon Berger, Thilo von Neumann et al.

Meeting transcription is a field of high relevance and remarkable progress in recent years. Still, challenges remain that limit its performance. In this work, we extend a previously proposed framework for analyzing leakage in speech separation with proper sensitivity to temporal locality. We show that there is significant leakage to the cross channel in areas where only the primary speaker is active. At the same time, the results demonstrate that this does not affect the final performance much as these leaked parts are largely ignored by the voice activity detection (VAD). Furthermore, different segmentations are compared showing that advanced diarization approaches are able to reduce the gap to oracle segmentation by a third compared to a simple energy-based VAD. We additionally reveal what factors contribute to the remaining difference. The results represent state-of-the-art performance on LibriCSS among systems that train the recognition module on LibriSpeech data only.

Peter Vieting, Benedikt Hilmes, Ralf Schlüter et al.

Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain heavily influenced by classical methods. While this inductive bias may ease the system design, our work aims to develop a more generic front-end for feature extraction. Furthermore, we seek to unify the front-end architecture contrasting with existing approaches that apply a composition of several layer topologies originating from different sources. The experiments systematically show how to reduce the influence of existing techniques to achieve a generic front-end. The resulting 2D convolutional front-end is parameter-efficient and suitable for a scenario with limited computational resources unlike large models pre-trained on unlabeled audio. The results demonstrate that this generic unified approach is not only feasible but also matches the performance of existing supervised learnable feature extractors.

Kristin Gnadt, David Thulke, Simone Kopeinik et al.

In recent years, various methods have been proposed to evaluate gender bias in large language models (LLMs). A key challenge lies in the transferability of bias measurement methods initially developed for the English language when applied to other languages. This work aims to contribute to this research strand by presenting five German datasets for gender bias evaluation in LLMs. The datasets are grounded in well-established concepts of gender bias and are accessible through multiple methodologies. Our findings, reported for eight multilingual LLM models, reveal unique challenges associated with gender bias in German, including the ambiguous interpretation of male occupational terms and the influence of seemingly neutral nouns on gender perception. This work contributes to the understanding of gender bias in LLMs across languages and underscores the necessity for tailored evaluation frameworks.

Nick Rossenbach, Benedikt Hilmes, Leon Brackmann et al.

Memristor-based hardware offers new possibilities for energy-efficient machine learning (ML) by providing analog in-memory matrix multiplication. Current hardware prototypes cannot fit large neural networks, and related literature covers only small ML models for tasks like MNIST or single word recognition. Simulation can be used to explore how hardware properties affect larger models, but existing software assumes simplified hardware. We propose a PyTorch-based library based on "Synaptogen" to simulate neural network execution with accurately captured memristor hardware properties. For the first time, we show how an ML system with millions of parameters would behave on memristor hardware, using a Conformer trained on the speech recognition task TED-LIUMv2 as example. With adjusted quantization-aware training, we limit the relative degradation in word error rate to 25% when using a 3-bit weight precision to execute linear operations via simulated analog computation.

Benedikt Hilmes, Nick Rossenbach, Ralf Schlüter

With the rise of large pre-trained foundation models for automatic speech recognition new challenges appear. While the performance of these models is good, runtime and cost of inference increases. One approach to make use of their strength while retaining efficiency is to distill their knowledge to smaller models during training. In this work, we explore different CTC-based distillation variants, focusing on blank token handling. We show that common approaches like blank elimination do not always work off the shelf. We explore new blank selection patterns as a potential sweet spot between standard knowledge distillation and blank elimination mechanisms. Through the introduction of a symmetric selection method, we are able to remove the CTC loss during knowledge distillation with minimal to no performance degradation. With this, we make the training independent from target labels, potentially allowing for distillation on untranscribed audio data.

Zijian Yang, Vahe Eminyan, Ralf Schlüter et al.

In statistical classification and machine learning, classification error is an important performance measure, which is minimized by the Bayes decision rule. In practice, the unknown true distribution is usually replaced with a model distribution estimated from the training data in the Bayes decision rule. This substitution introduces a mismatch between the Bayes error and the model-based classification error. In this work, we apply classification error bounds to study the relationship between the error mismatch and the Kullback-Leibler divergence in machine learning. Motivated by recent observations of low model-based classification errors in many machine learning tasks, bounding the Bayes error to be lower, we propose a linear approximation of the classification error bound for low Bayes error conditions. Then, the bound for class priors are discussed. Moreover, we extend the classification error bound for sequences. Using automatic speech recognition as a representative example of machine learning applications, this work analytically discusses the correlations among different performance measures with extended bounds, including cross-entropy loss, language model perplexity, and word error rate.

Wei Zhou, Eugen Beck, Simon Berger et al.

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only. For closed-vocabulary scenarios, public tools supporting lexical-constrained decoding are usually only for classical ASR, or do not support all S2S models. To eliminate this restriction on research possibilities such as modeling unit choice, we present RASR2 in this work, a research-oriented generic S2S decoder implemented in C++. It offers a strong flexibility/compatibility for various S2S models, language models, label units/topologies and neural network architectures. It provides efficient decoding for both open- and closed-vocabulary scenarios based on a generalized search framework with rich support for different search modes and settings. We evaluate RASR2 with a wide range of experiments on both switchboard and Librispeech corpora. Our source code is public online.

Tina Raissi, Eugen Beck, Ralf Schlüter et al.

In this work, we show that a factored hybrid hidden Markov model (FH-HMM) which is defined without any phonetic state-tying outperforms a state-of-the-art hybrid HMM. The factored hybrid HMM provides a link to transducer models in the way it models phonetic (label) context while preserving the strict separation of acoustic and language model of the hybrid HMM approach. Furthermore, we show that the factored hybrid model can be trained from scratch without using phonetic state-tying in any of the training steps. Our modeling approach enables triphone context while avoiding phonetic state-tying by a decomposition into locally normalized factored posteriors for monophones/HMM states in phoneme context. Experimental results are provided for Switchboard 300h and LibriSpeech. On the former task we also show that by avoiding the phonetic state-tying step, the factored hybrid can take better advantage of regularization techniques during training, compared to the standard hybrid HMM with phonetic state-tying based on classification and regression trees (CART).

Yu Qiao, Sourabh Zanwar, Rishab Bhattacharyya et al.

One of the key communicative competencies is the ability to maintain fluency in monologic speech and the ability to produce sophisticated language to argue a position convincingly. In this paper we aim to predict TED talk-style affective ratings in a crowdsourced dataset of argumentative speech consisting of 7 hours of speech from 110 individuals. The speech samples were elicited through task prompts relating to three debating topics. The samples received a total of 2211 ratings from 737 human raters pertaining to 14 affective categories. We present an effective approach to the classification task of predicting these categories through fine-tuning a model pre-trained on a large dataset of TED talks public speeches. We use a combination of fluency features derived from a state-of-the-art automatic speech recognition system and a large set of human-interpretable linguistic features obtained from an automatic text analysis system. Classification accuracy was greater than 60% for all 14 rating categories, with a peak performance of 72% for the rating category 'informative'. In a secondary experiment, we determined the relative importance of features from different groups using SP-LIME.

Zijian Yang, Yingbo Gao, Alexander Gerstenberger et al.

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based neural language models. These training criteria typically enjoy the benefit of faster training and testing, at a cost of slightly degraded performance in terms of perplexity and almost no visible drop in word error rate. While noise contrastive estimation is one of the most popular choices, recently we show that other sampling-based criteria can also perform well, as long as an extra correction step is done, where the intended class posterior probability is recovered from the raw model outputs. In this work, we propose self-normalized importance sampling. Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step. Through self-normalized language model training as well as lattice rescoring experiments, we show that our proposed self-normalized importance sampling is competitive in both research-oriented and production-oriented automatic speech recognition tasks.

Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher et al.

The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using conformer acoustic model for hybrid ASR is not investigated. In this paper, we present and evaluate a competitive conformer-based hybrid model training recipe. We study different training aspects and methods to improve word-error-rate as well as to increase training speed. We apply time downsampling methods for efficient training and use transposed convolutions to upsample the output sequence again. We conduct experiments on Switchboard 300h dataset and our conformer-based hybrid model achieves competitive results compared to other architectures. It generalizes very well on Hub5'01 test set and outperforms the BLSTM-based hybrid model significantly.

Felix Meyer, Wilfried Michel, Mohammad Zeineldeen et al.

To improve the performance of state-of-the-art automatic speech recognition systems it is common practice to include external knowledge sources such as language models or prior corrections. This is usually done via log-linear model combination using separate scaling parameters for each model. Typically these parameters are manually optimized on some held-out data. In this work we propose to optimize these scaling parameters via automatic differentiation and stochastic gradient decent similar to the neural network model parameters. We show on the LibriSpeech (LBS) and Switchboard (SWB) corpora that the model scales for a combination of attentionbased encoder-decoder acoustic model and language model can be learned as effectively as with manual tuning. We further extend this approach to subword dependent model scales which could not be tuned manually which leads to 7% improvement on LBS and 3% on SWB. We also show that joint training of scales and model parameters is possible and gives additional 6% improvement on LBS.

Nils-Philipp Wynands, Wilfried Michel, Jan Rosendahl et al.

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice. Current state-of-the-art systems with unlimited label context circumvent this problem by limiting the summation to an n-best list of relevant competing hypotheses obtained from beam search. This work proposes to perform (approximative) recombinations of hypotheses during beam search, if they share a common local history. The error that is incurred by the approximation is analyzed and it is shown that using this technique the effective beam size can be increased by several orders of magnitude without significantly increasing the computational requirements. Lastly, it is shown that this technique can be used to effectively perform sequence discriminative training for attention-based encoder-decoder acoustic models on the LibriSpeech task.

Wei Zhou, Zuoyun Zheng, Ralf Schlüter et al.

The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to remove this sequence prior as ILM correction. In this work, we study various ILM correction-based LM integration methods formulated in a common RNN-T framework. We provide a decoding interpretation on two major reasons for performance improvement with ILM correction, which is further experimentally verified with detailed analysis. We also propose an exact-ILM training framework by extending the proof given in the hybrid autoregressive transducer, which enables a theoretical justification for other ILM approaches. Systematic comparison is conducted for both in-domain and cross-domain evaluation on the Librispeech and TED-LIUM Release 2 corpora, respectively. Our proposed exact-ILM training can further improve the best ILM method.

Albert Zeyer, Ralf Schlüter, Hermann Ney

The peaky behavior of CTC models is well known experimentally. However, an understanding about why peaky behavior occurs is missing, and whether this is a good property. We provide a formal analysis of the peaky behavior and gradient descent convergence properties of the CTC loss and related training criteria. Our analysis provides a deep understanding why peaky behavior occurs and when it is suboptimal. On a simple example which should be trivial to learn for any model, we prove that a feed-forward neural network trained with CTC from uniform initialization converges towards peaky behavior with a 100% error rate. Our analysis further explains why CTC only works well together with the blank label. We further demonstrate that peaky behavior does not occur on other related losses including a label prior model, and that this improves convergence.

Yingbo Gao, David Thulke, Alexander Gerstenberger et al.

As the vocabulary size of modern word-based language models becomes ever larger, many sampling-based training criteria are proposed and investigated. The essence of these sampling methods is that the softmax-related traversal over the entire vocabulary can be simplified, giving speedups compared to the baseline. A problem we notice about the current landscape of such sampling methods is the lack of a systematic comparison and some myths about preferring one over another. In this work, we consider Monte Carlo sampling, importance sampling, a novel method we call compensated partial summation, and noise contrastive estimation. Linking back to the three traditional criteria, namely mean squared error, binary cross-entropy, and cross-entropy, we derive the theoretical solutions to the training problems. Contrary to some common belief, we show that all these sampling methods can perform equally well, as long as we correct for the intended class posterior probabilities. Experimental results in language modeling and automatic speech recognition on Switchboard and LibriSpeech support our claim, with all sampling-based methods showing similar perplexities and word error rates while giving the expected speedups.

Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng et al.

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that adapts the advantages of several text-based and acoustic-based subword methods into one pipeline. With a fully acoustic-oriented label design and learning process, ADSM produces acoustic-structured subword units and acoustic-matched target sequence for further ASR training. The obtained ADSM labels are evaluated with different end-to-end ASR approaches including CTC, RNN-Transducer and attention models. Experiments on the LibriSpeech corpus show that ADSM clearly outperforms both byte pair encoding (BPE) and pronunciation-assisted subword modeling (PASM) in all cases. Detailed analysis shows that ADSM achieves acoustically more logical word segmentation and more balanced sequence length, and thus, is suitable for both time-synchronous and label-synchronous models. We also briefly describe how to apply acoustic-based subword regularization and unseen text segmentation using ADSM.

Yu Qiao, Wei Zhou, Elma Kerz et al.

In recent years, automated approaches to assessing linguistic complexity in second language (L2) writing have made significant progress in gauging learner performance, predicting human ratings of the quality of learner productions, and benchmarking L2 development. In contrast, there is comparatively little work in the area of speaking, particularly with respect to fully automated approaches to assessing L2 spontaneous speech. While the importance of a well-performing ASR system is widely recognized, little research has been conducted to investigate the impact of its performance on subsequent automatic text analysis. In this paper, we focus on this issue and examine the impact of using a state-of-the-art ASR system for subsequent automatic analysis of linguistic complexity in spontaneously produced L2 speech. A set of 30 selected measures were considered, falling into four categories: syntactic, lexical, n-gram frequency, and information-theoretic measures. The agreement between the scores for these measures obtained on the basis of ASR-generated vs. manual transcriptions was determined through correlation analysis. A more differential effect of ASR performance on specific types of complexity measures when controlling for task type effects is also presented.

Wei Zhou, Albert Zeyer, André Merboldt et al.

With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a number of modeling architectures like encoder-decoder attention models, transducer models and segmental models (direct HMM). While transducer models stay with a frame-level model definition, segmental models are defined on the level of label segments directly. While (soft-)attention-based models avoid explicit alignment, transducer and segmental approach internally do model alignment, either by segment hypotheses or, more implicitly, by emitting so-called blank symbols. In this work, we prove that the widely used class of RNN-Transducer models and segmental models (direct HMM) are equivalent and therefore show equal modeling power. It is shown that blank probabilities translate into segment length probabilities and vice versa. In addition, we provide initial experiments investigating decoding and beam-pruning, comparing time-synchronous and label-/segment-synchronous search strategies and their properties using the same underlying model.

Mohammad Zeineldeen, Aleksandr Glushko, Wilfried Michel et al.

Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. The integration with an external LM trained on much more unpaired text usually leads to better performance. A Bayesian interpretation as in the hybrid autoregressive transducer (HAT) suggests dividing by the prior of the discriminative acoustic model, which corresponds to this implicit LM, similarly as in the hybrid hidden Markov model approach. The implicit LM cannot be calculated efficiently in general and it is yet unclear what are the best methods to estimate it. In this work, we compare different approaches from the literature and propose several novel methods to estimate the ILM directly from the AED model. Our proposed methods outperform all previous approaches. We also investigate other methods to suppress the ILM mainly by decreasing the capacity of the AED model, limiting the label context, and also by training the AED model together with a pre-existing LM.

Nick Rossenbach, Mohammad Zeineldeen, Benedikt Hilmes et al.

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to generate synthetic data with a trained text-to-speech system (TTS) if additional text is available. This was successfully applied in many publications with AED systems, but only very limited in the context of other ASR architectures. We investigate the effect of varying pre-processing, the speaker embedding and input encoding of the TTS system w.r.t. the effectiveness of the synthesized data for AED-ASR training. Additionally, we also consider internal language model subtraction for the first time, resulting in up to 38% relative improvement. We compare the AED results to a state-of-the-art hybrid ASR system, a monophone based system using connectionist-temporal-classification (CTC) and a monotonic transducer based system. We show that for the later systems the addition of synthetic data has no relevant effect, but they still outperform the AED systems on LibriSpeech-100h. We achieve a final word-error-rate of 3.3%/10.0% with a hybrid system on the clean/noisy test-sets, surpassing any previous state-of-the-art systems on Librispeech-100h that do not include unlabeled audio data.

Peter Vieting, Christoph Lüscher, Wilfried Michel et al.

With the success of neural network based modeling in automatic speech recognition (ASR), many studies investigated acoustic modeling and learning of feature extractors directly based on the raw waveform. Recently, one line of research has focused on unsupervised pre-training of feature extractors on audio-only data to improve downstream ASR performance. In this work, we investigate the usefulness of one of these front-end frameworks, namely wav2vec, in a setting without additional untranscribed data for hybrid ASR systems. We compare this framework both to the manually defined standard Gammatone feature set, as well as to features extracted as part of the acoustic model of an ASR system trained supervised. We study the benefits of using the pre-trained feature extractor and explore how to additionally exploit an existing acoustic model trained with different features. Finally, we systematically examine combinations of the described features in order to further advance the performance.

Albert Zeyer, André Merboldt, Wilfried Michel et al.

We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is justified by a Bayesian interpretation where the transducer model prior is given by the estimated internal LM. The subtraction of the internal LM gives us over 14% relative improvement over normal shallow fusion. Our transducer has a separate probability distribution for the non-blank labels which allows for easier combination with the external LM, and easier estimation of the internal LM. We additionally take care of including the end-of-sentence (EOS) probability of the external LM in the last blank probability which further improves the performance. All our code and setups are published.

Tina Raissi, Eugen Beck, Ralf Schlüter et al.

High-performance hybrid automatic speech recognition (ASR) systems are often trained with clustered triphone outputs, and thus require a complex training pipeline to generate the clustering. The same complex pipeline is often utilized in order to generate an alignment for use in frame-wise cross-entropy training. In this work, we propose a flat-start factored hybrid model trained by modeling the full set of triphone states explicitly without relying on clustering methods. This greatly simplifies the training of new models. Furthermore, we study the effect of different alignments used for Viterbi training. Our proposed models achieve competitive performance on the Switchboard task compared to systems using clustered triphones and other flat-start models in the literature.