We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages. Moreover, the model is able to transfer voices across languages, e.g. synthesize fluent Spanish speech using an English speaker's voice, without training on any bilingual or parallel examples. Such transfer works across distantly related languages, e.g. English and Mandarin.
Critical to achieving this result are: 1. using a phonemic input representation to encourage sharing of model capacity across languages, and 2. incorporating an adversarial loss term to encourage the model to disentangle its representation of speaker identity (which is perfectly correlated with language in the training data) from the speech content. Further scaling up the model by training on multiple speakers of each language, and incorporating an autoencoding input to help stabilize attention during training, results in a model which can be used to consistently synthesize intelligible speech for training speakers in all languages seen during training, and in native or foreign accents.
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…
Recent advances in neural TTS have led to models that can produce high-quality synthetic speech. However, these models typically require large amounts of training data, which can make it costly to produce a new voice with the desired quality. Although multi-speaker modeling can reduce the data requirements necessary for a new voice, this approach is usually not viable for many low-resource languages for which abundant multi-speaker data is not available. In this paper, we therefore investigated to what extent multilingual multi-speaker modeling can be an alternative to monolingual multi-speake…
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…
Duke University（杜克大学）；Duke Kunshan University（昆山杜克大学）
Modeling voices for multiple speakers and multiple languages in one text-to-speech system has been a challenge for a long time. This paper presents an extension on Tacotron2 to achieve bilingual multispeaker speech synthesis when there are limited data for each language. We achieve cross-lingual synthesis, including code-switching cases, between English and Mandarin for monolingual speakers. The two languages share the same phonemic representations for input, while the language attribute and the speaker identity are independently controlled by language tokens and speaker embeddings, respective…
Neosapience, Inc.（Neosapience公司）；Massachusetts Institute of Technology（麻省理工学院）
Although there are more than 6,500 languages in the world, the pronunciations of many phonemes sound similar across the languages. When people learn a foreign language, their pronunciation often reflects their native language's characteristics. This motivates us to investigate how the speech synthesis network learns the pronunciation from datasets from different languages. In this study, we are interested in analyzing and taking advantage of multilingual speech synthesis network. First, we train the speech synthesis network bilingually in English and Korean and analyze how the network learns t…
SOKENDAI (The Graduate University for Advanced Studies)（综合研究大学院大学（高等研究型大学））；National Institute of Informatics（国立信息学研究所）；The University of Edinburgh（爱丁堡大学）
Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we propose a methodology to bootstrap a VC system from a pretrained speaker-adaptive TTS model and unify the techniques as well as the interpretations of these two tasks. Moreover by offloading the heavy data demand to the training stage of the TTS model, our VC system can be built using a small amount of target speaker speech data. It also opens up the possibility …
The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approach is useful for code-switching, as it facilitates the seamless uttering of foreign text embedded in a stream of native text. In our work, we train a language-agnostic multispeaker model conditioned on a set of phonologically derived features common across different languages, with the goal of achieving cross-lingual speaker adaptation. We first experiment with the effect of language phonological similarity on cross-…
AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
Centre for Speech Technology Research, University of Edinburgh, UK（语音技术研究中心，爱丁堡大学，英国）；Department of AI Technology, Transsion, China（人工智能技术系，Transsion，中国）
This work addresses the problem of measuring how many languages a person "effectively" speaks given that some of the languages are close to each other. In other words, to assign a meaningful number to her language portfolio. Intuition says that someone who speaks fluently Spanish and Portuguese is linguistically less proficient compared to someone who speaks fluently Spanish and Chinese since it takes more effort for a native Spanish speaker to learn Chinese than Portuguese. As the number of languages grows and their proficiency levels vary, it gets even more complicated to assign a score to a…
Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. Its challenge lies in the fact that the source and target data are naturally non-parallel, and it is even difficult to bridge the gaps between languages with no transcriptions provided. In this paper, we focus on knowledge transfer from monolin-gual ASR to cross-lingual VC, in order to address the con-tent mismatch problem. To achieve this, we first train a monolingual acoustic model for the source language, use it to extract p…
One of the challenges in automatic speech recognition is foreign words recognition. It is observed that a speaker's pronunciation of a foreign word is influenced by his native language knowledge, and such phenomenon is known as the effect of language transfer. This paper focuses on examining the phonetic effect of language transfer in automatic speech recognition. A set of lexical rules is proposed to convert an English word into Mandarin phonetic representation. In this way, a Mandarin lexicon can be augmented by including English words. Hence, the Mandarin ASR system becomes capable to recog…
University of Oxford（牛津大学）；The Alan Turing Institute（艾伦·图灵研究所）；Barcelona Institute for Global Health (ISGlobal)（巴塞罗那全球健康研究所）；Universitat Pompeu Fabra（庞培法布拉大学）
The number and quality of user reviews greatly affects consumer purchasing decisions. While reviews in all languages are increasing, it is still often the case (especially for non-English speakers) that there are only a few reviews in a person's first language. Using an online experiment, we examine the value that potential purchasers receive from interfaces showing additional reviews in a second language. The results paint a complicated picture with both positive and negative reactions to the inclusion of foreign-language reviews. Roughly 26-28% of subjects clicked to see translations of the …
Indian Institute of Technology Kharagpur（印度理工学院克勒格布尔分校）；Microsoft Research India（微软印度研究院）
Code-mixing or code-switching are the effortless phenomena of natural switching between two or more languages in a single conversation. Use of a foreign word in a language; however, does not necessarily mean that the speaker is code-switching because often languages borrow lexical items from other languages. If a word is borrowed, it becomes a part of the lexicon of a language; whereas, during code-switching, the speaker is aware that the conversation involves foreign words or phrases. Identifying whether a foreign word used by a bilingual speaker is due to borrowing or code-switching is a fun…
Linked Multi-Modal Data on Russian Domestic and Foreign Policy Speeches
University of Delaware, Department of Political Science & International Relations（德克萨斯大学，政治科学与国际关系系）；University of Delaware, Masters of Science in Data Science Program（德克萨斯大学，数据科学硕士项目）；University of Delaware, Department of Computer & Information Sciences（德克萨斯大学，计算机与信息科学系）；University of Pennsylvania, Department of Political Science（宾夕法尼亚大学，政治科学系）
The motor theory of speech perception holds that we perceive the speech of another in terms of a motor representation of that speech. However, when we have learned to recognize a foreign accent, it seems plausible that recognition of a word rarely involves reconstruction of the speech gestures of the speaker rather than the listener. To better assess the motor theory and this observation, we proceed in three stages. Part 1 places the motor theory of speech perception in a larger framework based on our earlier models of the adaptive formation of mirror neurons for grasping, and for viewing exte…
We live in a world where 60% of the population can speak two or more languages fluently. Members of these communities constantly switch between languages when having a conversation. As automatic speech recognition (ASR) systems are being deployed to the real-world, there is a need for practical systems that can handle multiple languages both within an utterance or across utterances. In this paper, we present an end-to-end ASR system using a transformer-transducer model architecture for code-switched speech recognition. We propose three modifications over the vanilla model in order to handle va…
Carnegie Mellon University（卡内基梅隆大学）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Science（印度科学学院）
The problem of automatic accent identification is important for several applications like speaker profiling and recognition as well as for improving speech recognition systems. The accented nature of speech can be primarily attributed to the influence of the speaker's native language on the given speech recording. In this paper, we propose a novel accent identification system whose training exploits speech in native languages along with the accented speech. Specifically, we develop a deep Siamese network-based model which learns the association between accented speech recordings and the native…
Center for Information and Communication Technology（信息与通信技术中心）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
This work deals with non-native children's speech and investigates both multi-task and transfer learning approaches to adapt a multi-language Deep Neural Network (DNN) to speakers, specifically children, learning a foreign language. The application scenario is characterized by young students learning English and German and reading sentences in these second-languages, as well as in their mother language. The paper analyzes and discusses techniques for training effective DNN-based acoustic models starting from children native speech and performing adaptation with limited non-native audio materia…
This paper reports on the recognition component of an intelligent tutoring system that is designed to help foreign language speakers learn standard English. The system models the grammar of the learner, with this instantiation of the system tailored to signers of American Sign Language (ASL). We discuss the theoretical motivations for the system, various difficulties that have been encountered in the implementation, as well as the methods we have used to overcome these problems. Our method of capturing ungrammaticalities involves using mal-rules (also called 'error productions'). However, the …
