Suyoun Kim

Duc Le, Akshat Shrivastava, Paden Tomasello et al. · meta-ai

We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings. By formulating E2E SLU as a generalized decoder, our system is able to support complex compositional semantic structures. Furthermore, the sharing of parameters between ASR and NLU makes the system especially suitable for resource-constrained (on-device) environments; our proposed approach consistently outperforms strong pipeline NLU baselines by 0.60% to 0.65% on the spoken version of the TOPv2 dataset (STOP). We demonstrate that the fusion of text and audio features, coupled with the system's ability to rewrite the first-pass hypothesis, makes our approach more robust to ASR errors. Finally, we show that our approach can significantly reduce the degradation when moving from natural speech to synthetic speech training, but more work is required to make text-to-speech (TTS) a viable solution for scaling up E2E SLU.

Derek Xu, Shuyan Dong, Changhan Wang et al. · meta-ai, mit

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by utilizing rich semantic representations from the LLM. These systems come at the cost of labeled audio transcriptions, which is expensive and time-consuming to obtain. We propose a task-agnostic unsupervised way of incorporating semantic information from LLMs into self-supervised speech encoders without labeled audio transcriptions. By introducing semantics, we improve existing speech encoder spoken language understanding performance by over 10\% on intent classification, with modest gains in named entity resolution and slot filling, and spoken question answering FF1 score by over 2\%. Our unsupervised approach achieves similar performance as supervised methods trained on over 100 hours of labeled audio transcripts, demonstrating the feasibility of unsupervised semantic augmentations to existing speech encoders.

Suyoun Kim, Akshat Shrivastava, Duc Le et al. · meta-ai

End-to-end (E2E) spoken language understanding (SLU) systems that generate a semantic parse from speech have become more promising recently. This approach uses a single model that utilizes audio and text representations from pre-trained speech recognition models (ASR), and outperforms traditional pipeline SLU systems in on-device streaming scenarios. However, E2E SLU systems still show weakness when text representation quality is low due to ASR transcription errors. To overcome this issue, we propose a novel E2E SLU system that enhances robustness to ASR errors by fusing audio and text representations based on the estimated modality confidence of ASR hypotheses. We introduce two novel techniques: 1) an effective method to encode the quality of ASR hypotheses and 2) an effective approach to integrate them into E2E SLU models. We show accuracy improvements on STOP dataset and share the analysis to demonstrate the effectiveness of our approach.

Roshan Sharma, Suyoun Kim, Daniel Lazar et al. · meta-ai

Spoken semantic parsing (SSP) involves generating machine-comprehensible parses from input speech. Training robust models for existing application domains represented in training data or extending to new domains requires corresponding triplets of speech-transcript-semantic parse data, which is expensive to obtain. In this paper, we address this challenge by examining methods that can use transcript-semantic parse data (unpaired text) without corresponding speech. First, when unpaired text is drawn from existing textual corpora, Joint Audio Text (JAT) and Text-to-Speech (TTS) are compared as ways to generate speech representations for unpaired text. Experiments on the STOP dataset show that unpaired text from existing and new domains improves performance by 2% and 30% in absolute Exact Match (EM) respectively. Second, we consider the setting when unpaired text is not available in existing textual corpora. We propose to prompt Large Language Models (LLMs) to generate unpaired text for existing and new domains. Experiments show that examples and words that co-occur with intents can be used to generate unpaired text with Llama 2.0. Using the generated text with JAT and TTS for spoken semantic parsing improves EM on STOP by 1.4% and 2.6% absolute for existing and new domains respectively.

Suyoun Kim, Ke Li, Lucas Kabela et al.

Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy while keeping latency low. One of the latest 2nd-pass rescoring model, Transformer Rescorer, takes the n-best initial outputs and audio embeddings from the 1st-pass model, and then choose the best output by re-scoring the n-best initial outputs. However, training this Transformer Rescorer requires expensive paired audio-text training data because the model uses audio embeddings as input. In this work, we present our Joint Audio/Text training method for Transformer Rescorer, to leverage unpaired text-only data which is relatively cheaper than paired audio-text data. We evaluate Transformer Rescorer with our Joint Audio/Text training on Librispeech dataset as well as our large-scale in-house dataset and show that our training method can improve word error rate (WER) significantly compared to standard Transformer Rescorer without requiring any extra model parameters or latency.

Trang Le, Daniel Lazar, Suyoun Kim et al.

Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution. Previous works have explored end-to-end models to improve the quality and robustness of SLU models with Deliberation, however these models have remained autoregressive, resulting in higher latencies. In this work we introduce PRoDeliberation, a novel method leveraging a Connectionist Temporal Classification-based decoding strategy as well as a denoising objective to train robust non-autoregressive deliberation models. We show that PRoDeliberation achieves the latency reduction of parallel decoding (2-10x improvement over autoregressive models) while retaining the ability to correct Automatic Speech Recognition (ASR) mistranscriptions of autoregressive deliberation systems. We further show that the design of the denoising training allows PRoDeliberation to overcome the limitations of small ASR devices, and we provide analysis on the necessity of each component of the system.

Suyoun Kim, Duc Le, Weiyi Zheng et al.

Measuring automatic speech recognition (ASR) system quality is critical for creating user-satisfying voice-driven applications. Word Error Rate (WER) has been traditionally used to evaluate ASR system quality; however, it sometimes correlates poorly with user perception/judgement of transcription quality. This is because WER weighs every word equally and does not consider semantic correctness which has a higher impact on user perception. In this work, we propose evaluating ASR output hypotheses quality with SemDist that can measure semantic correctness by using the distance between the semantic vectors of the reference and hypothesis extracted from a pre-trained language model. Our experimental results of 71K and 36K user annotated ASR output quality show that SemDist achieves higher correlation with user perception than WER. We also show that SemDist has higher correlation with downstream Natural Language Understanding (NLU) tasks than WER.

Duc Le, Mahaveer Jain, Gil Keren et al.

How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to open-domain scenarios, did not scale to large biasing lists, or underperformed on rare long-tail words. We address these limitations by proposing a novel solution that combines shallow fusion, trie-based deep biasing, and neural network language model contextualization. These techniques result in significant 19.5% relative Word Error Rate improvement over existing contextual biasing approaches and 5.4%-9.3% improvement compared to a strong hybrid baseline on both open-domain and constrained contextualization tasks, where the targets consist of mostly rare long-tail words. Our final system remains lightweight and modular, allowing for quick modification without model re-training.

Suyoun Kim, Abhinav Arora, Duc Le et al.

Word Error Rate (WER) has been the predominant metric used to evaluate the performance of automatic speech recognition (ASR) systems. However, WER is sometimes not a good indicator for downstream Natural Language Understanding (NLU) tasks, such as intent recognition, slot filling, and semantic parsing in task-oriented dialog systems. This is because WER takes into consideration only literal correctness instead of semantic correctness, the latter of which is typically more important for these downstream tasks. In this study, we propose a novel Semantic Distance (SemDist) measure as an alternative evaluation metric for ASR systems to address this issue. We define SemDist as the distance between a reference and hypothesis pair in a sentence-level embedding space. To represent the reference and hypothesis as a sentence embedding, we exploit RoBERTa, a state-of-the-art pre-trained deep contextualized language model based on the transformer architecture. We demonstrate the effectiveness of our proposed metric on various downstream tasks, including intent recognition, semantic parsing, and named entity recognition.

Chunxi Liu, Frank Zhang, Duc Le et al.

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various benchmarks. In this work, we examine ways in which RNN-T can achieve better ASR accuracy via performing auxiliary tasks. We propose (i) using the same auxiliary task as primary RNN-T ASR task, and (ii) performing context-dependent graphemic state prediction as in conventional hybrid modeling. In transcribing social media videos with varying training data size, we first evaluate the streaming ASR performance on three languages: Romanian, Turkish and German. We find that both proposed methods provide consistent improvements. Next, we observe that both auxiliary tasks demonstrate efficacy in learning deep transformer encoders for RNN-T criterion, thus achieving competitive results - 2.0%/4.2% WER on LibriSpeech test-clean/other - as compared to prior top performing models.

Suyoun Kim, Yuan Shangguan, Jay Mahadeokar et al.

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has proposed various fusion methods to incorporate external NNLMs into end-to-end ASR to address this weakness. In this paper, we propose extensions to these techniques that allow RNN-T to exploit external NNLMs during both training and inference time, resulting in 13-18% relative Word Error Rate improvement on Librispeech compared to strong baselines. Furthermore, our methods do not incur extra algorithmic latency and allow for flexible plug-and-play of different NNLMs without re-training. We also share in-depth analysis to better understand the benefits of the different NNLM fusion methods. Our work provides a reliable technique for leveraging unpaired text data to significantly improve RNN-T while keeping the system streamable, flexible, and lightweight.

Suyoun Kim, Siddharth Dalmia, Florian Metze

We present an end-to-end speech recognition model that learns interaction between two speakers based on the turn-changing information. Unlike conventional speech recognition models, our model exploits two speakers' history of conversational-context information that spans across multiple turns within an end-to-end framework. Specifically, we propose a speaker-specific cross-attention mechanism that can look at the output of the other speaker side as well as the one of the current speaker for better at recognizing long conversations. We evaluated the models on the Switchboard conversational speech corpus and show that our model outperforms standard end-to-end speech recognition models.

Suyoun Kim, Siddharth Dalmia, Florian Metze

We present a novel conversational-context aware end-to-end speech recognizer based on a gated neural network that incorporates conversational-context/word/speech embeddings. Unlike conventional speech recognition models, our model learns longer conversational-context information that spans across sentences and is consequently better at recognizing long conversations. Specifically, we propose to use the text-based external word and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end framework, yielding a significant improvement in word error rate with better conversational-context representation. We evaluated the models on the Switchboard conversational speech corpus and show that our model outperforms standard end-to-end speech recognition models.

Suyoun Kim, Florian Metze

Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not capture important conversational context information. The recent progress in end-to-end speech recognition enables integrating context with other available information (e.g., acoustic, linguistic resources) and directly recognizing words from speech. In this work, we present a direct acoustic-to-word, end-to-end speech recognition model capable of utilizing the conversational context to better process long conversations. We evaluate our proposed approach on the Switchboard conversational speech corpus and show that our system outperforms a standard end-to-end speech recognition system.

Suyoun Kim, Florian Metze

Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The recent progress in end-to-end speech recognition systems promises to integrate all available information (e.g. acoustic, language resources) into a single model, which is then jointly optimized. It seems natural that such dialog context information should thus also be integrated into the end-to-end models to improve further recognition accuracy. In this work, we present a dialog-context aware speech recognition model, which explicitly uses context information beyond sentence-level information, in an end-to-end fashion. Our dialog-context model captures a history of sentence-level context so that the whole system can be trained with dialog-context information in an end-to-end manner. We evaluate our proposed approach on the Switchboard conversational speech corpus and show that our system outperforms a comparable sentence-level end-to-end speech recognition system.

Suyoun Kim, Michael L. Seltzer, Jinyu Li et al.

Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training. Otherwise, the networks may fail to find a good local optimum. This is particularly true for online networks, such as unidirectional LSTMs. Currently, the best strategy to train such systems is to bootstrap the training from a tied-triphone system. However, this is time consuming, and more importantly, is impossible for languages without a high-quality pronunciation lexicon. In this work, we propose an initialization strategy that uses teacher-student learning to transfer knowledge from a large, well-trained, offline end-to-end speech recognition model to an online end-to-end model, eliminating the need for a lexicon or any other linguistic resources. We also explore curriculum learning and label smoothing and show how they can be combined with the proposed teacher-student learning for further improvements. We evaluate our methods on a Microsoft Cortana personal assistant task and show that the proposed method results in a 19 % relative improvement in word error rate compared to a randomly-initialized baseline system.

Suyoun Kim, Michael L. Seltzer

Building speech recognizers in multiple languages typically involves replicating a monolingual training recipe for each language, or utilizing a multi-task learning approach where models for different languages have separate output labels but share some internal parameters. In this work, we exploit recent progress in end-to-end speech recognition to create a single multilingual speech recognition system capable of recognizing any of the languages seen in training. To do so, we propose the use of a universal character set that is shared among all languages. We also create a language-specific gating mechanism within the network that can modulate the network's internal representations in a language-specific way. We evaluate our proposed approach on the Microsoft Cortana task across three languages and show that our system outperforms both the individual monolingual systems and systems built with a multi-task learning approach. We also show that this model can be used to initialize a monolingual speech recognizer, and can be used to create a bilingual model for use in code-switching scenarios.

Suyoun Kim, Takaaki Hori, Shinji Watanabe

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between variable-length input and output sequences in one step using a purely data-driven method. The attention model has often been shown to improve the performance over another end-to-end approach, the Connectionist Temporal Classification (CTC), mainly because it explicitly uses the history of the target character without any conditional independence assumptions. However, we observed that the performance of the attention has shown poor results in noisy condition and is hard to learn in the initial training stage with long input sequences. This is because the attention model is too flexible to predict proper alignments in such cases due to the lack of left-to-right constraints as used in CTC. This paper presents a novel method for end-to-end speech recognition to improve robustness and achieve fast convergence by using a joint CTC-attention model within the multi-task learning framework, thereby mitigating the alignment issue. An experiment on the WSJ and CHiME-4 tasks demonstrates its advantages over both the CTC and attention-based encoder-decoder baselines, showing 5.4-14.6% relative improvements in Character Error Rate (CER).

Suyoun Kim, Bhiksha Raj, Ian Lane

We propose a novel deep neural network architecture for speech recognition that explicitly employs knowledge of the background environmental noise within a deep neural network acoustic model. A deep neural network is used to predict the acoustic environment in which the system in being used. The discriminative embedding generated at the bottleneck layer of this network is then concatenated with traditional acoustic features as input to a deep neural network acoustic model. Through a series of experiments on Resource Management, CHiME-3 task, and Aurora4, we show that the proposed approach significantly improves speech recognition accuracy in noisy and highly reverberant environments, outperforming multi-condition training, noise-aware training, i-vector framework, and multi-task learning on both in-domain noise and unseen noise.

Suyoun Kim, Ian Lane

Integration of multiple microphone data is one of the key ways to achieve robust speech recognition in noisy environments or when the speaker is located at some distance from the input device. Signal processing techniques such as beamforming are widely used to extract a speech signal of interest from background noise. These techniques, however, are highly dependent on prior spatial information about the microphones and the environment in which the system is being used. In this work, we present a neural attention network that directly combines multi-channel audio to generate phonetic states without requiring any prior knowledge of the microphone layout or any explicit signal preprocessing for speech enhancement. We embed an attention mechanism within a Recurrent Neural Network (RNN) based acoustic model to automatically tune its attention to a more reliable input source. Unlike traditional multi-channel preprocessing, our system can be optimized towards the desired output in one step. Although attention-based models have recently achieved impressive results on sequence-to-sequence learning, no attention mechanisms have previously been applied to learn potentially asynchronous and non-stationary multiple inputs. We evaluate our neural attention model on the CHiME-3 challenge task, and show that the model achieves comparable performance to beamforming using a purely data-driven method.

Seungwhan Moon, Suyoun Kim, Haohan Wang

We propose a transfer deep learning (TDL) framework that can transfer the knowledge obtained from a single-modal neural network to a network with a different modality. Specifically, we show that we can leverage speech data to fine-tune the network trained for video recognition, given an initial set of audio-video parallel dataset within the same semantics. Our approach first learns the analogy-preserving embeddings between the abstract representations learned from intermediate layers of each network, allowing for semantics-level transfer between the source and target modalities. We then apply our neural network operation that fine-tunes the target network with the additional knowledge transferred from the source network, while keeping the topology of the target network unchanged. While we present an audio-visual recognition task as an application of our approach, our framework is flexible and thus can work with any multimodal dataset, or with any already-existing deep networks that share the common underlying semantics. In this work in progress report, we aim to provide comprehensive results of different configurations of the proposed approach on two widely used audio-visual datasets, and we discuss potential applications of the proposed approach.