In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. Additionally, we propose a novel alignment regularization technique that promotes synchronization of the audio and visual encoder, which in turn results in better word error rates (WERs) at all SNR levels for streaming and offline AV-ASR models. The proposed AV-ASR model achieves WERs of 2.0% and 2.6% on the Lip Reading Sentences 3 (LRS3) dataset in an offline and online setup, respectively, which both present state-of-the-art results when no external training data are used.
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 us…
In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio encoding with no lookahead or right context and an additional stack of transformer layers on top trained with variable right context. In inference time, the context length for the variable context layers can be changed to trade off the latency and the accuracy of the model. We also show that we can run this model in a Y-model architecture with the top layers r…
We present a unified and hardware efficient architecture for two stage voice trigger detection (VTD) and false trigger mitigation (FTM) tasks. Two stage VTD systems of voice assistants can get falsely activated to audio segments acoustically similar to the trigger phrase of interest. FTM systems cancel such activations by using post trigger audio context. Traditional FTM systems rely on automatic speech recognition lattices which are computationally expensive to obtain on device. We propose a streaming transformer (TF) encoder architecture, which progressively processes incoming audio chunks a…
Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing approaches including Early and Late Penalties and Constrained Alignments penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models. While being successful in reducing delay, these approaches suffer from significant accuracy regression and also require additional word alignment information from an exis…
Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing. However, when it comes to performing run-on recognition on an input stream of audio data while producing recognition results in real-time and with low word-based latency, these models face several challenges. For many techniques, the whole audio sequence to be decoded needs to be available at the start of the processing, e.g., for the attention mechanism or th…
Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional information to improve a recurrent neural network-transducer (RNN-T) based automatic speech recognition (ASR) system. An audio-to-intent (A2I) model encodes the intent of the utterance in the form of embeddings or posteriors, and these are used as auxiliary inputs for RNN-T training and inference. Experimenting with a 50k-hour far-field English speech corpus, this s…
There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal alignment of the training transcripts and audio. As a result, RNN-T models built with uni-directional long short term memory (LSTM) encoders tend to wait for longer spans of input audio, before streaming already decoded ASR tokens. In this work, we propose a modification to the RNN-T loss function and develop Alignment Restricted RNN-T (Ar-RNN-T) models, whic…
All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the ability of E2E models to generalize to unseen domains, where we find that models trained on short utterances fail to generalize to long-form speech. We propose two complementary solutions to address this: training on diverse acoustic data, and LSTM state manipulation to simulate long-form audio when training using short utterances. On a synthesized long-form…
Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with no future context, compared to their non-streaming counterparts. Consequently, streaming models usually perform worse than non-streaming models. We propose a novel and effective learning method by leveraging a non-streaming ASR model as a teacher to generate transcripts on an arbitrarily large data set, which is then used to distill knowledge into streaming A…
King’s College London（伦敦国王学院）；Blekinge Institute of Technology（布莱金厄理工学院）；University of Portsmouth（朴茨茅斯大学）；University of Plymouth（普利茅斯大学）
Modern streaming services are increasingly labeling videos based on their visual or audio content. This typically augments the use of technologies such as AI and ML by allowing to use natural speech for searching by keywords and video descriptions. Prior research has successfully provided a number of solutions for speech to text, in the case of a human speech, but this article aims to investigate possible solutions to retrieve sound events based on a natural language query, and estimate how effective and accurate they are. In this study, we specifically focus on the YamNet, AlexNet, and ResNet…
We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or partially labeled sequences of the stream during training. We show that the use of context audio during training and inference can lead to word error rate reductions of more than 6% in a realistic production setting for a voice assistant ASR system. We investigate the effect of the proposed training approach on acoustically challenging data containing background sp…
Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover adequately the long tail of linguistic content that's important for tasks such as open-ended dictation and voice search. We seek to address both the streaming and the tail recognition challenges by using a language model (LM) trained on unpaired text data to enhance the end-to-end (E2E) model. We extend shallow fusion and cold fusion approaches to streaming Recurrent…
Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future input context. Previous research has shown that streaming and non-streaming ASR for RNN Transducers can be unified by cascading causal and non-causal encoders. This work improves upon this cascaded encoders framework by leveraging two streaming non-causal encoders with variable input context sizes that can produce outputs at different audio intervals (e.g. f…
Graduate School of Informatics, Kyoto University（京都大学信息学研究生院）
We investigate a monotonic multihead attention (MMA) by extending hard monotonic attention to Transformer-based automatic speech recognition (ASR) for online streaming applications. For streaming inference, all monotonic attention (MA) heads should learn proper alignments because the next token is not generated until all heads detect the corresponding token boundaries. However, we found not all MA heads learn alignments with a naïve implementation. To encourage every head to learn alignments properly, we propose HeadDrop regularization by masking out a part of heads stochastically during train…
Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming End-to-End ASR models. However, the pivotal characteristics of SSL is to be utilized for any untranscribed audio data. In this paper, we provide a full exploration on how to utilize uncurated audio data in SSL from data pre-processing to deploying an streaming hybrid ASR model. More specifically, we present (1) the effect of Audio Event Detection (AED) model in da…
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）；International Audio Laboratories Erlangen（埃尔朗根国际音频实验室）
Broadcasting and streaming services still suffer from various levels of accessibility barriers for a significant portion of the population, limiting the access to information and culture, and in the most severe cases limiting the empowerment of people. This paper provides a brief overview of some of the most common accessibility barriers encountered. It then gives a short introduction to object-based audio (OBA) production and transport, focusing on the aspects relevant for lowering accessibility barriers. MPEG-H Audio is used as a concrete example of an OBA system already deployed. Two exampl…
Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild. To support a large variety of downstream audio tasks, such as real-time ASR and audio-call enhancement, a PSE solution should operate in a streaming mode, i.e., input audio cleaning should happen in real-time with a small latency and real-time factor. Personalisation is typically achieved by extracting a target speaker's voice profile from an enrolment audio, in the for…
We propose Mobile Audio Streaming Networks (MASnet) for efficient low-latency speech enhancement, which is particularly suitable for mobile devices and other applications where computational capacity is a limitation. MASnet processes linear-scale spectrograms, transforming successive noisy frames into complex-valued ratio masks which are then applied to the respective noisy frames. MASnet can operate in a low-latency incremental inference mode which matches the complexity of layer-by-layer batch mode. Compared to a similar fully-convolutional architecture, MASnet incorporates depthwise and poi…
Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enough to be deployed on the diverse variety of edge devices with their equally diverse computational capacities. To address this, we propose FBWave, a family of efficient and scalable neural vocoders that can achieve optimal performance-efficiency trade-offs for different edge devices. FBWave is a hybrid flow-based generative model that combines the advantages of autoregressive and non-autoregressive models. It produces …
Seoul National University（首尔大学）；Artificial Intelligence Institute, Seoul National University（首尔大学人工智能研究院）
In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive regularization that is designed to be target task-oriented and trained simultaneously. In addition, we propose an audio mixing based simple augmentation strategy that performed in batch samples. Experimental results validate that the proposed method successfully contributed to the performance improvement, and particularly showed that it has advantages in sta…
In this paper, we examine the use of Transfer Learning using Pretrained Audio Neural Networks (PANNs), and propose an architecture that is able to better leverage the acoustic features provided by PANNs for the Automated Audio Captioning Task. We also introduce a novel self-supervised objective, Reconstruction Latent Space Similarity Regularization (RLSSR). The RLSSR module supplements the training of the model by minimizing the similarity between the encoder and decoder embedding. The combination of both methods allows us to surpass state of the art results by a significant margin on the Clot…
ByteDance（字节跳动）；Georgia Institute of Technology（佐治亚理工学院）
Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if sufficient training data is available, as specific task-relevant properties can be learned. Furthermore, the complex pre-trained models bring considerable computational burdens during inference. We propose to leverage both detailed task-specific features from spectrogram input and generic pre-trained features by introducing two regularization methods that integrate…
Beijing University of Posts and Telecommunications（北京邮电大学）；Ludong University（鲁东大学）
Audio captioning aims at describing the content of audio clips with human language. Due to the ambiguity of audio, different people may perceive the same audio differently, resulting in caption disparities (i.e., one audio may correlate to several captions with diverse semantics). For that, general audio captioning models achieve the one-to-many training by randomly selecting a correlated caption as the ground truth for each audio. However, it leads to a significant variation in the optimization directions and weakens the model stability. To eliminate this negative effect, in this paper, we pr…
Dialogue-Based Streaming Audio-Visual Target Speaker Extraction with Predictive Dialogue Information
Shenzhen Loop Area Institute（深圳河套学院）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）；The Chinese University of Hong Kong（香港中文大学）
Neural end-to-end (E2E) models have become a promising technique to realize practical automatic speech recognition (ASR) systems. When realizing such a system, one important issue is the segmentation of audio to deal with streaming input or long recording. After audio segmentation, the ASR model with a small real-time factor (RTF) is preferable because the latency of the system can be faster. Recently, E2E ASR based on non-autoregressive models becomes a promising approach since it can decode an $N$-length token sequence with less than $N$ iterations. We propose a system to concatenate audio s…
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
Center for Language and Speech Processing, Johns Hopkins University, USA（语言与语音处理中心，约翰霍普金斯大学，美国）；Signal Analysis and Interpretation Laboratory, University of Southern California, USA（信号分析与解释实验室，南加州大学，美国）
Deep learning models are mostly used in an offline inference fashion. However, this strongly limits the use of these models inside audio generation setups, as most creative workflows are based on real-time digital signal processing. Although approaches based on recurrent networks can be naturally adapted to this buffer-based computation, the use of convolutions still poses some serious challenges. To tackle this issue, the use of causal streaming convolutions have been proposed. However, this requires specific complexified training and can impact the resulting audio quality. In this paper, we …
Speech emotion recognition is a challenge and an important step towards more natural human-computer interaction (HCI). The popular approach is multimodal emotion recognition based on model-level fusion, which means that the multimodal signals can be encoded to acquire embeddings, and then the embeddings are concatenated together for the final classification. However, due to the influence of noise or other factors, each modality does not always tend to the same emotional category, which affects the generalization of a model. In this paper, we propose a novel regularization method via contrastiv…
General-purpose embedding is highly desirable for few-shot even zero-shot learning in many application scenarios, including audio tasks. In order to understand representations better, we conducted a thorough error analysis and visualization of HEAR 2021 submission results. Inspired by the analysis, this work experiments with different front-end audio preprocessing methods, including Constant-Q Transform (CQT) and Short-time Fourier transform (STFT), and proposes a Batch Embedding Covariance Regularization (BECR) term to uncover a more holistic simulation of the frequency information received b…
TO-Rawnet: Improving RawNet with TCN and Orthogonal Regularization for Fake Audio Detection
University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）
