Tina Raissi

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.

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.

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.

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).

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.

Valentin Mendelev, Tina Raissi, Guglielmo Camporese et al.

Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to speech disfluencies with a focus on partial words. For evaluation we use clean data, data with disfluencies and a separate dataset with speech affected by stuttering. We show that after including a small amount of data with disfluencies in the training set the recognition accuracy on the tests with disfluencies and stuttering improves. Increasing the amount of training data with disfluencies gives additional gains without degradation on the clean data. We also show that replacing partial words with a dedicated token helps to get even better accuracy on utterances with disfluencies and stutter. The evaluation of our best model shows 22.5% and 16.4% relative WER reduction on those two evaluation sets.

Tina Raissi, Eugen Beck, Ralf Schlüter et al.

Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their highly varying statistics require tying or smoothing to enable robust training. Usually, classification and regression trees are used for phonetic clustering, which is standard in hidden Markov model (HMM)-based systems. However, this solution introduces a secondary training objective and does not allow for end-to-end training. In this work, we address a direct phonetic context modeling for the hybrid deep neural network (DNN)/HMM, that does not build on any phone clustering algorithm for the determination of the HMM state inventory. By performing different decompositions of the joint probability of the center phoneme state and its left and right contexts, we obtain a factorized network consisting of different components, trained jointly. Moreover, the representation of the phonetic context for the network relies on phoneme embeddings. The recognition accuracy of our proposed models on the Switchboard task is comparable and outperforms slightly the hybrid model using the standard state-tying decision trees.

Tina Raissi, Santiago Pascual, Maurizio Omologo

In many applications of multi-microphone multi-device processing, the synchronization among different input channels can be affected by the lack of a common clock and isolated drops of samples. In this work, we address the issue of sample drop detection in the context of a conversational speech scenario, recorded by a set of microphones distributed in space. The goal is to design a neural-based model that given a short window in the time domain, detects whether one or more devices have been subjected to a sample drop event. The candidate time windows are selected from a set of large time intervals, possibly including a sample drop, and by using a preprocessing step. The latter is based on the application of normalized cross-correlation between signals acquired by different devices. The architecture of the neural network relies on a CNN-LSTM encoder, followed by multi-head attention. The experiments are conducted using both artificial and real data. Our proposed approach obtained F1 score of 88% on an evaluation set extracted from the CHiME-5 corpus. A comparable performance was found in a larger set of experiments conducted on a set of multi-channel artificial scenes.

Tina Raissi, Alessandro Tibo, Paolo Bientinesi

We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no longer organized in a waterfall scheme. The whole system is realized by traversing backtrack arrows and cycles between various stages. In order to give a compact and effective representation of the features, the standard early temporal integration is combined with other selection and extraction phases: on the one hand, the selection of the most meaningful characteristics based on information gain, and on the other hand, the inclusion of the nonlinear correlation between this subset of features, determined by an autoencoder. The results of the experiments conducted on GTZAN dataset reveal a noticeable contribution of this methodology towards the model's performance in classification task.