End-to-end speech recognition with Alignment RNN-Transducer

The recurrent neural network transducer (RNN-T) model has been proved effective for keyword spotting (KWS) recently. However, compared with cross-entropy (CE) or connectionist temporal classification (CTC) based models, the additional prediction network in the RNN-T model increases the model size and computational cost. Besides, since the keyword training data usually only contain the keyword sequence, the prediction network might has over-fitting problems. In this paper, we improve the RNN-T modeling for small-footprint keyword spotting in three aspects. First, to address the over-fitting issue, we explore multi-task training where a CTC loss is added to the encoder. The CTC loss is calculated with both KWS data and ASR data, while the RNN-T loss is calculated with ASR data so that only the encoder is augmented with KWS data. Second, we use the feed-forward neural network to replace the LSTM for prediction network modeling. Thus all possible prediction network outputs could be pre-computed for decoding. Third, we further improve the model with transfer learning, where a model trained with 160 thousand hours of ASR data is used to initialize the KWS model. On a self-collected far-field wake-word testset, the proposed RNN-T system greatly improves the performance comparing with a strong "keyword-filler" baseline.

The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR). To estimate the output distributions over subword units, RNN-T uses a fully connected layer as the joint network to fuse the acoustic representations extracted using the acoustic encoder with the text representations obtained using the prediction network based on the previous subword units. In this paper, we propose to use gating, bilinear pooling, and a combination of them in the joint network to produce more expressive representations to feed into the output layer. A regularisation method is also proposed to enable better acoustic encoder training by reducing the gradients back-propagated into the prediction network at the beginning of RNN-T training. Experimental results on a multilingual ASR setting for voice search over nine languages show that the joint use of the proposed methods can result in 4%--5% relative word error rate reductions with only a few million extra parameters.

This article describes a density ratio approach to integrating external Language Models (LMs) into end-to-end models for Automatic Speech Recognition (ASR). Applied to a Recurrent Neural Network Transducer (RNN-T) ASR model trained on a given domain, a matched in-domain RNN-LM, and a target domain RNN-LM, the proposed method uses Bayes' Rule to define RNN-T posteriors for the target domain, in a manner directly analogous to the classic hybrid model for ASR based on Deep Neural Networks (DNNs) or LSTMs in the Hidden Markov Model (HMM) framework (Bourlard & Morgan, 1994). The proposed approach is evaluated in cross-domain and limited-data scenarios, for which a significant amount of target domain text data is used for LM training, but only limited (or no) {audio, transcript} training data pairs are used to train the RNN-T. Specifically, an RNN-T model trained on paired audio & transcript data from YouTube is evaluated for its ability to generalize to Voice Search data. The Density Ratio method was found to consistently outperform the dominant approach to LM and end-to-end ASR integration, Shallow Fusion.

We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly learns acoustic and language model components. Our models are trained to predict either phonemes or graphemes as subword units, thus allowing us to detect arbitrary keyword phrases, without any out-of-vocabulary words. In order to adapt the models to the requirements of keyword spotting, we propose a novel technique which biases the RNN-T system towards a specific keyword of interest. Our systems are compared against a strong sequence-trained, connectionist temporal classification (CTC) based "keyword-filler" baseline, which is augmented with a separate phoneme language model. Overall, our RNN-T system with the proposed biasing technique significantly improves performance over the baseline system.

Recent advancements in large language models (LLMs) such as ChatGPT have contributed to the development of chatbot systems.Specifically, speech has been recognized as the optimal tool for interactive dialogue, leading to increased interest in voice chatbots.Voice chatbots offer information and services through voice interactions, enhancing user experience and improving service accessibility.This survey paper introduces the latest developments in the core technologies of voice chatbot systems, including deep learning-based automatic speech recognition, speech synthesis, and speech emotion recognition.It focuses on advanced research to enhance speed and performance, which is crucial for applying speech technologies in voice chatbots.In automatic speech recognition, we introduce methodologies such as Connectionist Temporal Classification (CTC), Attention based Encoder-Decoder (AED), and Recurrent Neural Network Transducer (RNN-T), along with studies optimizing Transformerbased models for real-time automatic speech recognition.In speech emotion recognition, we explore the use of pre-trained models and the latest techniques for accurate emotion prediction.For speech synthesis, the focus extends to two-stage and End-to-End (E2E) approaches, with additional research on integrating emotional information to generate natural speech.

In this paper we present an end-to-end speech recognition system that can recognize single-channel speech where multiple talkers can speak at the same time (overlapping speech) by using a neural network model based on Recurrent Neural Network Transducer (RNN-T) architecture. We augment the conventional RNN-T architecture by including a masking model for separation of encoded audio features, and multiple label encoders to encode transcripts from different speakers. We use a masking L2 loss to prevent transcripts to align to wrong speakers’ audio, and a speaker embedding loss to facilitate speaker tracking. We show that by using these additional training objectives, the proposed augmented RNN-T model can be trained with simulated overlapping speech data and can achieve a WER of 32% on words in overlapping speech segments from real-life telephone conversations. Our analysis of manual transcription task on the same test set shows that transcribing overlapping speech is hard even for humans who can get a WER of 37% compared to ground-truth.

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parameters than a conventional ASR system, thus making it suitable for on-device applications. For example, recurrent neural network transducer (RNN-T) as a streaming E2E model has shown promising potential for on-device ASR [1]. For such applications, quality and latency are two critical factors. We propose to reduce E2E model's latency by extending the RNN-T endpointer (RNN-T EP) model [2] with additional early and late penalties. By further applying the minimum word error rate (MWER) training technique [3], we achieved 8.0% relative word error rate (WER) reduction and 130ms 90-percentile latency reduction over [2] on a Voice Search test set. We also experimented with a second-pass Listen, Attend and Spell (LAS) rescorer [4]. Although it did not directly improve the first pass latency, the large WER reduction provides extra room to trade WER for latency. RNN-T EP+LAS, together with MWER training brings in 18.7% relative WER reduction and 160ms 90-percentile latency reductions compared to the original proposed RNN-T EP [2] model.

End-to-end models have significant potential in most languages and recently proved the robustness in ASR tasks. Many robust architectures are proposed, and among many techniques, Recurrent Neural Network - Transducer (RNN-T) shows remarkable success. However, with background noise or reverb in spontaneous speech, this architecture generally suffers from high deletion error problems. For this reason, we propose the blank label re-weighting technique to improve the state-of-the-art Conformer transducer model. Our proposed system adopts the Stochastic Weight Averaging approach, stabilizing the training process. Our work achieved the first rank with a 4.17% of word error rate in Task 2 of the VLSP 2021 Competition.

Non-native speech causes automatic speech recognition systems to degrade in performance. Past strategies to address this challenge have considered model adaptation, accent classification with a model selection, alternate pronunciation lexicon, etc. In this study, we consider a recurrent neural network (RNN) with connectionist temporal classification (CTC) cost function trained on multi-accent English data including US (Native), Indian and Hispanic accents. We exploit dark knowledge from a model trained with the multi-accent data to train student models under the guidance of both a teacher model and CTC cost of target transcription. We show that transferring knowledge from a single RNN-CTC trained model toward a student model, yields better performance than the stand-alone teacher model. Since the outputs of different trained CTC models are not necessarily aligned, it is not possible to simply use an ensemble of CTC teacher models. To address this problem, we train accent specific models under the guidance of a single multi-accent teacher, which results in having multiple aligned and trained CTC models. Furthermore, we train a student model under the supervision of the accent-specific teachers, resulting in an even further complementary model, which achieves +20.1% relative Character Error Rate (CER) reduction compared to the baseline trained without any teacher. Having this effective multi-accent model, we can achieve further improvement for each accent by adapting the model to each accent. Using the accent specific model's outputs to regularize the adapting process (i.e., a knowledge distillation version of Kullback-Leibler (KL) divergence) results in even superior performance compared to the conventional approach using general teacher models.

In this paper, we present a comparative study on the robustness of two different online streaming speech recognition models: Monotonic Chunkwise Attention (MoChA) and Recurrent Neural Network-Transducer (RNN-T). We explore three recently proposed data augmentation techniques, namely, multi-conditioned training using an acoustic simulator, Vocal Tract Length Perturbation (VTLP) for speaker variability, and SpecAugment. Experimental results show that unidirectional models are in general more sensitive to noisy examples in the training set. It is observed that the final performance of the model depends on the proportion of training examples processed by data augmentation techniques. MoChA models generally perform better than RNN-T models. However, we observe that training of MoChA models seems to be more sensitive to various factors such as the characteristics of training sets and the incorporation of additional augmentations techniques. On the other hand, RNN-T models perform better than MoChA models in terms of latency, inference time, and the stability of training. Additionally, RNN-T models are generally more robust against noise and reverberation. All these advantages make RNN-T models a better choice for streaming on-device speech recognition compared to MoChA models.

An investigation of neural uncertainty estimation for target speaker extraction equipped RNN transducer

In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this case, conventional approaches usually address this problem in a cascaded fashion that involves speech separation, speech recognition and speaker identification that are trained independently. In this paper, we propose Streaming Unmixing, Recognition and Identification Transducer (SURIT) -- a new framework that deals with this problem in an end-to-end streaming fashion. SURIT employs the recurrent neural network transducer (RNN-T) as the backbone for both speech recognition and speaker identification. We validate our idea on the LibrispeechMix dataset -- a multi-talker dataset derived from Librispeech, and present encouraging results.

Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec 2.0 requires a two-stage pipeline. In this paper we demonstrate a single-stage training of ASR models that can utilize both unlabeled and labeled data. During training, we alternately minimize two losses: an unsupervised masked Contrastive Predictive Coding (CPC) loss and the supervised audio-to-text alignment loss Connectionist Temporal Classification (CTC). We show that this joint training method directly optimizes performance for the downstream ASR task using unsupervised data while achieving similar word error rates to wav2vec 2.0 on the Librispeech 100-hours dataset. Finally, we postulate that solving the contrastive task is a regularization for the supervised CTC loss.

The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC model relies on the current input and does not account for context weighted inputs. This is the hard alignment issue. Second, the word-based CTC model suffers from the out-of-vocabulary (OOV) issue. This means it can model only frequently occurring words while tagging the remaining words as OOV. Hence, such a model is limited in its capacity in recognizing only a fixed set of frequent words. In this study, we propose addressing these problems using a combination of attention mechanism and mixed-units. In particular, we introduce Attention CTC, Self-Attention CTC, Hybrid CTC, and Mixed-unit CTC. First, we blend attention modeling capabilities directly into the CTC network using Attention CTC and Self-Attention CTC. Second, to alleviate the OOV issue, we present Hybrid CTC which uses a word and letter CTC with shared hidden layers. The Hybrid CTC consults the letter CTC when the word CTC emits an OOV. Then, we propose a much better solution by training a Mixed-unit CTC which decomposes all the OOV words into sequences of frequent words and multi-letter units. Evaluated on a 3400 hours Microsoft Cortana voice assistant task, our final acoustic-to-word solution using attention and mixed-units achieves a relative reduction in word error rate (WER) over the vanilla word CTC by 12.09\%. Such an E2E model without using any language model (LM) or complex decoder also outperforms a traditional context-dependent (CD) phoneme CTC with strong LM and decoder by 6.79% relative.

We introduce two techniques, length perturbation and n-best based label smoothing, to improve generalization of deep neural network (DNN) acoustic models for automatic speech recognition (ASR). Length perturbation is a data augmentation algorithm that randomly drops and inserts frames of an utterance to alter the length of the speech feature sequence. N-best based label smoothing randomly injects noise to ground truth labels during training in order to avoid overfitting, where the noisy labels are generated from n-best hypotheses. We evaluate these two techniques extensively on the 300-hour Switchboard (SWB300) dataset and an in-house 500-hour Japanese (JPN500) dataset using recurrent neural network transducer (RNNT) acoustic models for ASR. We show that both techniques improve the generalization of RNNT models individually and they can also be complementary. In particular, they yield good improvements over a strong SWB300 baseline and give state-of-art performance on SWB300 using RNNT models.