Efficient Training for Cross-lingual Speech Language Models
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院计算技术研究所智能信息处理重点实验室）；State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所人工智能安全国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
目前，大型语言模型主要聚焦文本模态。为实现更自然的人机交互，语音大模型正在兴起，但构建有效的端到端语音大模型仍具挑战性，因数据有限且扩展至更多语言困难。本文介绍Cross-lingual Speech Language Model (CSLM)，一种基于离散语音标记的多语言语音大模型高效训练方法。我们提出一种新的对齐策略，通过持续预训练实现跨模态和跨语言对齐。通过遵循语音-文本交错的生成流程进行指令微调，我们增强了更细粒度的模态对齐，从而提升生成质量并减少延迟。CSLM能够在无需大量语音数据的情况下同时对齐不同模态和语言，从而展现出良好的语言扩展能力。在跨模态任务、单语言对话任务和跨语言对话任务上的评估表明，CSLM在跨模态对齐能力和通用任务能力方面表现强劲。(代码可在: https://github.com/ictnlp/CSLM 获取)
英文摘要：
Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data and the difficulty in expanding to more languages. In this paper, we introduce Cross-lingual Speech Language Model (CSLM), an efficient training method for cross-lingual speech LLMs based on discrete speech tokens. We propose a novel alignment strategy that achieves cross-modal and cross-lingual alignment through continual pre-training. By conducting instruction fine-tuning following a speech-text interleaved chain-of-modality generation process, we enhance modal alignment at a finer granularity, thereby improving generation quality and reducing latency. CSLM aligns different modalities and languages simultaneously without the need for massive speech data, thus exhibiting good language scalability. Evaluations on cross-modal tasks, mono-lingual conversational tasks, and cross-lingual conversational tasks demonstrate CSLM's strong cross-modal alignment capabilities and general task abilities. (Code is available at: https://github.com/ictnlp/CSLM)
Multi-lingual speech recognition aims to distinguish linguistic expressions in different languages and integrate acoustic processing simultaneously. In contrast, current multi-lingual speech recognition research follows a language-aware paradigm, mainly targeted to improve recognition performance rather than discriminate language characteristics. In this paper, we present a multi-lingual speech recognition network named Mixture-of-Language-Expert(MoLE), which digests speech in a variety of languages. Specifically, MoLE analyzes linguistic expression from input speech in arbitrary languages, ac…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Le Mans University（勒芒大学）
We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation learning, which learns multilingual contextual speech embedding at the resolution of an acoustic frame (10-20ms), this work focuses on learning multimodal (speech-text) multilingual speech embedding at the resolution of a sentence (5-10s) such that the embedding vector space is semantically aligned across different languages. We combine state-of-the-art multilingual acoustic frame-level speech representation learning mo…
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are attractive because of their simplicity and elegance. While it is possible to integrate traditional multi-lingual bottleneck feature extractors as front-ends, we show that end-to-end multi-lingual training of sequence models is effective on context independent models trained using Connectionist Temporal Classification (CTC) loss. We show that our model impro…
This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to …
State-of-the-art automatic speech recognition (ASR) systems perform well on healthy speech. However, the performance on impaired speech still remains an issue. The current study explores the usefulness of using Wav2Vec self-supervised speech representations as features for training an ASR system for dysarthric speech. Dysarthric speech recognition is particularly difficult as several aspects of speech such as articulation, prosody and phonation can be impaired. Specifically, we train an acoustic model with features extracted from Wav2Vec, Hubert, and the cross-lingual XLSR model. Results sugge…
This paper presents XLS-R, a large-scale model for cross-lingual speech representation learning based on wav2vec 2.0. We train models with up to 2B parameters on nearly half a million hours of publicly available speech audio in 128 languages, an order of magnitude more public data than the largest known prior work. Our evaluation covers a wide range of tasks, domains, data regimes and languages, both high and low-resource. On the CoVoST-2 speech translation benchmark, we improve the previous state of the art by an average of 7.4 BLEU over 21 translation directions into English. For speech reco…
Athena Research Center（雅典研究中心）；Behavioral Signal Technologies（行为信号技术公司）；National and Kapodistrian University of Athens（雅典国立卡波季斯特里亚大学）
Aphasia is a common speech and language disorder, typically caused by a brain injury or a stroke, that affects millions of people worldwide. Detecting and assessing Aphasia in patients is a difficult, time-consuming process, and numerous attempts to automate it have been made, the most successful using machine learning models trained on aphasic speech data. Like in many medical applications, aphasic speech data is scarce and the problem is exacerbated in so-called "low resource" languages, which are, for this task, most languages excluding English. We attempt to leverage available data in Engl…
In the recent years end to end (E2E) automatic speech recognition (ASR) systems have achieved promising results given sufficient resources. Even for languages where not a lot of labelled data is available, state of the art E2E ASR systems can be developed by pretraining on huge amounts of high resource languages and finetune on low resource languages. For a lot of low resource languages the current approaches are still challenging, since in many cases labelled data is not available in open domain. In this paper we present an approach to create labelled data for Maithili, Bhojpuri and Dogri by …
Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on understanding the languages behaviour in the multilingual speech recognition setups. In this paper, a novel data-driven approach is proposed to investigate the cross-lingual acoustic-phonetic similarities. This technique measures the similarities between posterior distributions from various monolingual acoustic models against a target speech signal. Deep neural net…
The sparsely-gated Mixture of Experts (MoE) can magnify a network capacity with a little computational complexity. In this work, we investigate how multi-lingual Automatic Speech Recognition (ASR) networks can be scaled up with a simple routing algorithm in order to achieve better accuracy. More specifically, we apply the sparsely-gated MoE technique to two types of networks: Sequence-to-Sequence Transformer (S2S-T) and Transformer Transducer (T-T). We demonstrate through a set of ASR experiments on multiple language data that the MoE networks can reduce the relative word error rates by 16.3% …
Tokyo Institute of Technology（东京工业大学）；Microsoft（微软）；Microsoft Research Asia（微软亚洲研究院）；Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；Zhejiang University（浙江大学）
Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition models can easily overfit. In this paper, we propose to use adapters to investigate the performance of multiple adapters for parameter-efficient cross-lingual speech adaptation. Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters. Our algorithm levera…
University of Science and Technology of China（中国科学技术大学）；National Engineering Laboratory for Speech and Language Information Processing（国家语音与语言信息处理工程实验室）
In this paper, we propose a weakly supervised multilingual representation learning framework, called cross-lingual self-training (XLST). XLST is able to utilize a small amount of annotated data from high-resource languages to improve the representation learning on multilingual un-annotated data. Specifically, XLST uses a supervised trained model to produce initial representations and another model to learn from them, by maximizing the similarity between output embeddings of these two models. Furthermore, the moving average mechanism and multi-view data augmentation are employed, which are expe…
Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models. Cross-lingual transfer is an attractive solution to this problem, because low-resource languages can potentially benefit from higher-resource languages either through transfer learning, or being jointly trained in the same multilingual model. The problem of cross-lingual transfer has been well studied in ASR, however, recent advances in Self Supervised Learni…
Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during beam-search decoding, and have been found to recognize rare named entities poorly. The problem is exacerbated when biasing towards proper nouns in foreign languages, e.g., geographic location names, which are virtually unseen in training and are thus out-of-vocabulary (OOV). While grapheme or wordpiece E2E models might have a difficult time spelling OOV words, phonem…
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…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UC Santa Barbara（加州大学圣巴巴拉分校）；National Taiwan University（台湾大学）
Self-supervised speech representation learning (speech SSL) has demonstrated the benefit of scale in learning rich representations for Automatic Speech Recognition (ASR) with limited paired data, such as wav2vec 2.0. We investigate the existence of sparse subnetworks in pre-trained speech SSL models that achieve even better low-resource ASR results. However, directly applying widely adopted pruning methods such as the Lottery Ticket Hypothesis (LTH) is suboptimal in the computational cost needed. Moreover, we show that the discovered subnetworks yield minimal performance gain compared to the o…
This paper investigates the applications of various multilingual approaches developed in conventional hidden Markov model (HMM) systems to sequence-to-sequence (seq2seq) automatic speech recognition (ASR). On a set composed of Babel data, we first show the effectiveness of multi-lingual training with stacked bottle-neck (SBN) features. Then we explore various architectures and training strategies of multi-lingual seq2seq models based on CTC-attention networks including combinations of output layer, CTC and/or attention component re-training. We also investigate the effectiveness of language-tr…
National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
End-to-end speech-to-intent classification has shown its advantage in harvesting information from both text and speech. In this paper, we study a technique to develop such an end-to-end system that supports multiple languages. To overcome the scarcity of multi-lingual speech corpus, we exploit knowledge from a pre-trained multi-lingual natural language processing model. Multi-lingual bidirectional encoder representations from transformers (mBERT) models are trained on multiple languages and hence expected to perform well in the multi-lingual scenario. In this work, we employ a teacher-student …
Baidu Inc.（百度公司）；University of Chinese Academy of Sciences（中国科学院大学）；University of Waterloo（滑铁卢大学）；Oregon State University（俄勒冈州立大学）
Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks, including cross-lingual multi-speaker voice cloning and cross-lingual multi-speaker speech editing. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes given a speech example and its transcription. By learning to reconstruct the masked parts of the …
We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the target language speech by using both the source language speech and the target language text as prompts. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. Experimental results show that it can generate high-quality speech in the ta…
Speech processing systems currently do not support the vast majority of languages, in part due to the lack of data in low-resource languages. Cross-lingual transfer offers a compelling way to help bridge this digital divide by incorporating high-resource data into low-resource systems. Current cross-lingual algorithms have shown success in text-based tasks and speech-related tasks over some low-resource languages. However, scaling up speech systems to support hundreds of low-resource languages remains unsolved. To help bridge this gap, we propose a language similarity approach that can efficie…
Recent advances in cross-lingual text-to-speech (TTS) made it possible to synthesize speech in a language foreign to a monolingual speaker. However, there is still a large gap between the pronunciation of generated cross-lingual speech and that of native speakers in terms of naturalness and intelligibility. In this paper, a triplet training scheme is proposed to enhance the cross-lingual pronunciation by allowing previously unseen content and speaker combinations to be seen during training. Proposed method introduces an extra fine-tune stage with triplet loss during training, which efficiently…
The Experimental High School Attached to Beijing Normal University（北京师范大学附属实验中学）
A speech emotion recognition algorithm based on multi-feature and Multi-lingual fusion is proposed in order to resolve low recognition accuracy caused by lack of large speech dataset and low robustness of acoustic features in the recognition of speech emotion. First, handcrafted and deep automatic features are extracted from existing data in Chinese and English speech emotions. Then, the various features are fused respectively. Finally, the fused features of different languages are fused again and trained in a classification model. Distinguishing the fused features with the unfused ones, the r…
Recently, sequence-to-sequence (seq-to-seq) models have been successfully applied in text-to-speech (TTS) to synthesize speech for single-language text. To synthesize speech for multiple languages usually requires multi-lingual speech from the target speaker. However, it is both laborious and expensive to collect high-quality multi-lingual TTS data for the target speakers. In this paper, we proposed to use low-quality code-switched found data from the non-target speakers to achieve cross-lingual voice cloning for the target speakers. Experiments show that our proposed method can generate high-…
National Institute of Informatics（国立信息学研究所）；SOKENDAI (The Graduate University for Advanced Studies)（综合研究大学院大学（高等研究生院大学））
As the recently proposed voice cloning system, NAUTILUS, is capable of cloning unseen voices using untranscribed speech, we investigate the feasibility of using it to develop a unified cross-lingual TTS/VC system. Cross-lingual speech generation is the scenario in which speech utterances are generated with the voices of target speakers in a language not spoken by them originally. This type of system is not simply cloning the voice of the target speaker, but essentially creating a new voice that can be considered better than the original under a specific framing. By using a well-trained English…
Most hate speech detection research focuses on a single language, generally English, which limits their generalisability to other languages. In this paper we investigate the cross-lingual hate speech detection task, tackling the problem by adapting the hate speech resources from one language to another. We propose a cross-lingual capsule network learning model coupled with extra domain-specific lexical semantics for hate speech (CCNL-Ex). Our model achieves state-of-the-art performance on benchmark datasets from AMI@Evalita2018 and AMI@Ibereval2018 involving three languages: English, Spanish a…
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…
Hate speech detection within a cross-lingual setting represents a paramount area of interest for all medium and large-scale online platforms. Failing to properly address this issue on a global scale has already led over time to morally questionable real-life events, human deaths, and the perpetuation of hate itself. This paper illustrates the capabilities of fine-tuned altered multi-lingual Transformer models (mBERT, XLM-RoBERTa) regarding this crucial social data science task with cross-lingual training from English to French, vice-versa and each language on its own, including sections about …
POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation
Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University（天津大学认知计算与应用天津市重点实验室）；Nanyang Technological University（南洋理工大学）；Huiyan Technology Company, Ltd.（慧眼科技有限公司）；Chinese Academy of Sciences（中国科学院）；Tibet University（西藏大学）
Research on multilingual speech emotion recognition faces the problem that most available speech corpora differ from each other in important ways, such as annotation methods or interaction scenarios. These inconsistencies complicate building a multilingual system. We present results for cross-lingual and multilingual emotion recognition on English and French speech data with similar characteristics in terms of interaction (human-human conversations). Further, we explore the possibility of fine-tuning a pre-trained cross-lingual model with only a small number of samples from the target language…
Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease
FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；UT Austin（奥斯汀大学）；CMU（卡内基梅隆大学）；Czech Technical University in Prague（布拉格技术大学）；Idiap Research Institute（Idiap研究机构）；Universidad de Antioquia（安提奥基亚大学）；Shenzhen Loop Area Institute（深圳河套学院）；Fortemedia（Fortemedia公司）
Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised visual representation learning. We use the recently-proposed Raw Audio-Visual Speech Encoders (RAVEn) framework to pre-train an audio-visual model with unlabelled multilingual data, and then fine-tune the visual model on labelled transcriptions. Our experiments show that: (1) multi-lingual models with more data outperform monolingual ones, but, when keeping th…
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；Stellenbosch University（斯泰伦博斯大学）
Given a large amount of unannotated speech in a low-resource language, can we classify the speech utterances by topic? We consider this question in the setting where a small amount of speech in the low-resource language is paired with text translations in a high-resource language. We develop an effective cross-lingual topic classifier by training on just 20 hours of translated speech, using a recent model for direct speech-to-text translation. While the translations are poor, they are still good enough to correctly classify the topic of 1-minute speech segments over 70% of the time - a 20% imp…
Department of Computer Science, Columbia University（哥伦比亚大学计算机科学系）
The majority of existing speech emotion recognition models are trained and evaluated on a single corpus and a single language setting. These systems do not perform as well when applied in a cross-corpus and cross-language scenario. This paper presents results for speech emotion recognition for 4 languages in both single corpus and cross corpus setting. Additionally, since multi-task learning (MTL) with gender, naturalness and arousal as auxiliary tasks has shown to enhance the generalisation capabilities of the emotion models, this paper introduces language ID as another auxiliary task in MTL …
ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion
Coqui（Coqui公司）；QuintoAndar（QuintoAndar公司）；Darmstadt University of Applied Sciences（达姆施塔特应用技术大学）；São Paulo State University（圣保罗州立大学）；Federal University of Goiás（戈亚斯联邦大学）；Mercado Livre（自由市场公司）
Nara Institute of Science and Technology（奈良科学技术研究所）；RIKEN Center for Advanced Intelligence Project AIP（理化学研究所高级智能项目AIP中心）
Even though over seven hundred ethnic languages are spoken in Indonesia, the available technology remains limited that could support communication within indigenous communities as well as with people outside the villages. As a result, indigenous communities still face isolation due to cultural barriers; languages continue to disappear. To accelerate communication, speech-to-speech translation (S2ST) technology is one approach that can overcome language barriers. However, S2ST systems require machine translation (MT), speech recognition (ASR), and synthesis (TTS) that rely heavily on supervised…
University of Augsburg（奥格斯堡大学）；TU Munich（慕尼黑工业大学）；Imperial College London（帝国理工学院）
Detecting hate speech, especially in low-resource languages, is a non-trivial challenge. To tackle this, we developed a tailored architecture based on frozen, pre-trained Transformers to examine cross-lingual zero-shot and few-shot learning, in addition to uni-lingual learning, on the HatEval challenge data set. With our novel attention-based classification block AXEL, we demonstrate highly competitive results on the English and Spanish subsets. We also re-sample the English subset, enabling additional, meaningful comparisons in the future.
