End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance drops substantially. However, transcripts are not always available, and how significant such pretraining is for E2E ST has rarely been studied in the literature. In this paper, we revisit this question and explore the extent to which the quality of E2E ST trained on speech-translation pairs alone can be improved. We reexamine several techniques proven beneficial to ST previously, and offer a set of best practices that biases a Transformer-based E2E ST system toward training from scratch. Besides, we propose parameterized distance penalty to facilitate the modeling of locality in the self-attention model for speech. On four benchmarks covering 23 languages, our experiments show that, without using any transcripts or pretraining, the proposed system reaches and even outperforms previous studies adopting pretraining, although the gap remains in (extremely) low-resource settings. Finally, we discuss neural acoustic feature modeling, where a neural model is designed to extract acoustic features from raw speech signals directly, with the goal to simplify inductive biases and add freedom to the model in describing speech. For the first time, we demonstrate its feasibility and show encouraging results on ST tasks.
In this work, we compare from-scratch sequence-level cross-entropy (full-sum) training of Hidden Markov Model (HMM) and Connectionist Temporal Classification (CTC) topologies for automatic speech recognition (ASR). Besides accuracy, we further analyze their capability for generating high-quality time alignment between the speech signal and the transcription, which can be crucial for many subsequent applications. Moreover, we propose several methods to improve convergence of from-scratch full-sum training by addressing the alignment modeling issue. Systematic comparison is conducted on both Swi…
Brno University of Technology（布尔诺理工大学）；NTT Corporation（日本电信电话株式会社）
In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output stream separately. In this work, we argue that such a scheme is sub-optimal and propose a principled solution that decodes all speakers jointly. We modify the acoustic model to predict joint state posteriors for all speakers, enabling the network to express uncertainty about the attribution of parts of the speech signal to the speakers. We employ a joint decod…
Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?
Barcelona Supercomputing Center, Spain（巴塞罗那超级计算中心，西班牙）；Universitat Politècnica de Catalunya, Spain（加泰罗尼亚理工大学，西班牙）；DFKI GmbH, Saarland Informatics Campus, Saarbrücken, Germany（德意志联邦计算机研究中心（DFKI） GmbH，萨尔布吕肯，德国）
Two-Stage Adaptation for Non-Normative Speech Recognition: Revisiting Speaker-Independent Initialization for Personalization
Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands（莱顿先进计算机科学研究所，莱顿大学，荷兰）；Penobscot Community Health Care, United States（彭纳波克社区医疗服务，美国）；Department of Computational Linguistics, University of Zurich, Switzerland（计算语言学系，苏黎世大学，瑞士）
Nagoya University（名古屋大学）；Academia Sinica（中央研究院）；National Taiwan University of Science and Technology（台湾科技大学）
We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given a history context sequence, a powerful LM can narrow the range of possible choices and the speech signal can be used as a simple clue. Hence, comparing to conventional ASR systems that train a powerful acoustic model (AM) from scratch, we believe that speech recognition is possible by simply fine-tuning a BERT model. As an initial study, we demonstrate the e…
We introduce CVSS, a massively multilingual-to-English speech-to-speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the Common Voice speech corpus and the CoVoST 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems. Two versions of translation speeches are provided: 1) CVSS-C: All the translation speeches are in a single high-quality canonical voice; 2) CVSS-T: The translation speeches are in voices transferred from the correspon…
McGill University（麦吉尔大学）；Mila（米拉人工智能研究院）；Facebook AI Research（脸书人工智能研究院）；Apple（苹果公司）
Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems. In this work, we extend pseudo-labeling to massively multilingual speech recognition with 60 languages. We propose a simple pseudo-labeling recipe that works well even with low-resource languages: train a supervised multilingual model, fine-tune it with semi-supervised learning on a target language, generate pseudo-labels for that language, and train a final model using pseudo-labels for all languages, either from scratch or by fine-tuning. Experiments on the labeled…
Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptation of models across multiple different speech recognition tasks, in this paper we propose an experimental setting for \textit{online continual learning} for automatic speech recognition of a single task. Specifically focusing on the case where additional training data for the same task becomes available incrementally over time, we demonstrate the effectiveness of performing inc…
Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight memory of compute-constrained devices. We demonstrate the effectiveness of S3RL on a keyword-spotting (KS) problem by using transformers with 330k parameters and propose a mechanism to enhance utterance-wise distinction, which proves crucial for improving performance on classification tasks. On the Google speech commands v2 dataset, the proposed method appli…
Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different modalities, languages and application domains, foundation models have demonstrated strong generalization and knowledge transfer capabilities. In this paper, we present a pioneering study towards building an efficient solution for FM-based speech recognition systems. We adopt the recently developed self-supervised BEST-RQ for pretraining, and propose the joint fine…
University of Nairobi（内罗毕大学）；Maseno University（马塞诺大学）；Africa Nazarene University（非洲拿撒勒大学）
Building automatic speech recognition (ASR) systems is a challenging task, especially for under-resourced languages that need to construct corpora nearly from scratch and lack sufficient training data. It has emerged that several African indigenous languages, including Kiswahili, are technologically under-resourced. ASR systems are crucial, particularly for the hearing-impaired persons who can benefit from having transcripts in their native languages. However, the absence of transcribed speech datasets has complicated efforts to develop ASR models for these indigenous languages. This paper exp…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a large source language, and transferring to the low resource target language. In this work, we introduced an adaptive activation network to the upper layers of ASR model, and applied different activation functions to different languages. We also proposed two approaches to train the model: (1) cross-lingual learning, replacing the activation function from source l…
Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
University of Trento（特伦托大学）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎综合理工学院电信巴黎分校LTCI实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；Universite Paris-Saclay, LISN, CNRS（巴黎萨克雷大学LISN实验室，法国国家科学研究中心）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given model. It can be used to effectively initialize the encoder of an Automatic Speech Recognition (ASR) model. We present a novel modification of CPC called Guided Contrastive Predictive Coding (GCPC). Our proposed method maximizes the mutual information between representations from a prior-knowledge model and the output of the model being pre-trained, allowing prior knowledge injection during pre-training. We validate …
Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party problem. In this paper, we present a state-of-the-art monaural multi-speaker end-to-end automatic speech recognition model. In contrast to previous studies on the monaural multi-speaker speech recognition, this end-to-end framework is trained to recognize multiple label sequences completely from scratch. The system only requires the speech mixture and correspo…
Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several unsupervised pre-training models have been proposed, applying such models directly might still be sub-optimal if more labeled, training data could be obtained without a large cost. In this paper, we present a weakly supervised framework for constructing ASR systems with massive video data. As videos often contain human-speech audios aligned with subtitles, w…
Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the mapping from the input sequence to the output sequence from scratch, without the assumption of prior knowledge such as the alignments. However, this model is prone to overfitting, especially when the amount of training data is limited. Inspired by SpecAugment and BERT, in this paper, we propose a semantic mask based regularization for training such kind of end-…
Institute of Artificial Intelligence Research, Qihoo of Beijing Science and Technology Co. Ltd.（北京奇虎科技有限公司人工智能研究院）
Historically lower-level tasks such as automatic speech recognition (ASR) and speaker identification are the main focus in the speech field. Interest has been growing in higher-level spoken language understanding (SLU) tasks recently, like sentiment analysis (SA). However, improving performances on SLU tasks remains a big challenge. Basically, there are two main methods for SLU tasks: (1) Two-stage method, which uses a speech model to transfer speech to text, then uses a language model to get the results of downstream tasks; (2) One-stage method, which just fine-tunes a pre-trained speech mode…
Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT-2, have become a key technology for many natural language processing tasks. In this paper, we present results using fine-tuned GPT, GPT-2, and their combination for automatic speech recognition (ASR). Unlike unidirectional LM GPT and GPT-2, BERT is bidirectional whose direct product of the output probabilities is no longer a valid language prior probability. A conversion method is proposed to compute the correct langu…
The performance of child speech recognition is generally less satisfactory compared to adult speech due to limited amount of training data. Significant performance degradation is expected when applying an automatic speech recognition (ASR) system trained on adult speech to child speech directly, as a result of domain mismatch. The present study is focused on adult-to-child acoustic feature conversion to alleviate this mismatch. Different acoustic feature conversion approaches, including deep neural network based and signal processing based, are investigated and compared under a fair experiment…
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time. Therefore, this work focuses on ASR with output compression, a task challenging for supervised approaches due to the scarcity of training data. We first investigate a cascaded system, where an unsupervised compression model is used to post-edit the transcribed speech. We then compare several methods of end-to-end speech recognition under output length constr…
Tohoku University of Community Service and Science（东北公益文科大学）；Kitami Institute of Technology（北见工业大学）；Yokohama National University（横滨国立大学）
In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data from related language(s) is available. While the technology has a potential for facilitating tasks carried out in language documentation projects, such as speech transcription, pretraining a multilingual model from scratch for every new language would be highly impractical. We investigate the possibility for adapting an existing multilingual wav2vec 2.0 model fo…
Designing a speech-to-intent (S2I) agent which maps the users' spoken commands to the agents' desired task actions can be challenging due to the diverse grammatical and lexical preference of different users. As a remedy, we discuss a user-taught S2I system in this paper. The user-taught system learns from scratch from the users' spoken input with action demonstration, which ensure it is fully matched to the users' way of formulating intents and their articulation habits. The main issue is the scarce training data due to the user effort involved. Existing state-of-art approaches in this setting…
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Temasek Laboratories, Nanyang Technological University（南洋理工大学淡马锡实验室）
To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the back-end in this paper. One of the advantage of the proposed method is that the entire system can be trained from scratch. Different from prior works, either component here doesn't need to perform pre-training and fine-tuning processes separately. Through analysis, we found that the success of the proposed method lies in the following aspects. Firstly, multitask le…
Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited by the need for large labelled audiovisual datasets (in each downstream domain of interest). We present AVFormer, a simple method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We do this by (i) injecting visual embeddings into a frozen ASR model using lightweight trainable adaptors. We sh…
International Phonetic Alphabet (IPA) has been widely used in cross-lingual text-to-speech (TTS) to achieve cross-lingual voice cloning (CL VC). However, IPA itself has been understudied in cross-lingual TTS. In this paper, we report some empirical findings of building a cross-lingual TTS model using IPA as inputs. Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance. Furthermore, we find that using a dataset including one speaker per language to build an IPA-based TTS system would fail CL VC since the language-unique IPA…
Laboratoire d’Informatique de l’Université du Mans (LIUM)（勒芒大学计算机实验室）；Aix Marseille Univ（艾克斯-马赛大学）；Université de Toulon（土伦大学）；CNRS（法国国家科学研究中心）；LIS（计算机与系统实验室）；Institut National de l'Audiovisuel (INA)（法国国家视听研究院）；Naver Labs Europe (NLE)（Naver欧洲实验室）
We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech. We leverage the INA (French National Audiovisual Institute) collection and obtain 19GB of text after applying ASR on 350,000 hours of diverse TV shows. From this, spoken language models are trained either by fine-tuning an existing LM (FlauBERT) or through training a LM from scratch. New models (FlauBERT-Oral) are shared with the community and evaluated for 3 downstream tasks: spoken language understanding, classification of TV shows and speech syntactic parsing. Results show that Fla…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the sequence-to-sequence architecture, the model is trained to predict the grapheme of the current time-step given the input of speech signal and the ground-truth grapheme history of the previous time-steps. However, it remains unclear how well the model approximates real-world speech during inference. Thus, generating the whole transcription from scratch based on previou…
Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS)（弗劳恩霍夫智能分析与信息系统研究所）
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks in domains that greatly deviate from the conditions represented by the training data. For many real-world applications, there is a lack of sufficient data that can be directly used for training robust speech recognition systems. To address this issue, we propose and investigate an approach that performs a robust acoustic model adaption to a target domain in…
Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. This work explores the idea of building a single domain-invariant model for varied use-cases by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate e…
Radboud University（拉德堡德大学）；Delft University of Technology（代尔夫特理工大学）
Background: Computational models of speech recognition often assume that the set of target words is already given. This implies that these models do not learn to recognise speech from scratch without prior knowledge and explicit supervision. Visually grounded speech models learn to recognise speech without prior knowledge by exploiting statistical dependencies between spoken and visual input. While it has previously been shown that visually grounded speech models learn to recognise the presence of words in the input, we explicitly investigate such a model as a model of human speech recognition…
In spoken language understanding (SLU), what the user says is converted to his/her intent. Recent work on end-to-end SLU has shown that accuracy can be improved via pre-training approaches. We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch. Hence we fine-tune on speech only for the word module, and we apply multi-target le…
