相关论文: FLEURS-R: A Restored Multilingual Speech Corpus fo…

Despite impressive advancements in multilingual corpora collection and model training, developing large-scale deployments of multilingual models still presents a significant challenge. This is particularly true for language tasks that are…

We introduce the Speak & Improve Corpus 2025, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform. The aim of the…

Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voice exemplars, allowing the model to mimic speaker identity,…

Only a handful of the world's languages are abundant with the resources that enable practical applications of speech processing technologies. One of the methods to overcome this problem is to use the resources existing in other languages to…

Large language models (LLMs) are increasingly used to access legal information. Yet, their deployment in multilingual legal settings is constrained by unreliable retrieval and the lack of domain-adapted, open-embedding models. In…

Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across…

Recent progress in speech processing has highlighted that high-quality performance across languages requires substantial training data for each individual language. While existing multilingual datasets cover many languages, they often…

This paper introduces F5-TTS, a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT). Without requiring complex designs such as duration model, text encoder, and phoneme alignment, the text…

Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast,…

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of…

We present SuperPivot, an analysis method for low-resource languages that occur in a superparallel corpus, i.e., in a corpus that contains an order of magnitude more languages than parallel corpora currently in use. We show that SuperPivot…

We introduce LibriTTS-P, a new corpus based on LibriTTS-R that includes utterance-level descriptions (i.e., prompts) of speaking style and speaker-level prompts of speaker characteristics. We employ a hybrid approach to construct prompt…

The goal of this work is zero-shot text-to-speech synthesis, with speaking styles and voices learnt from facial characteristics. Inspired by the natural fact that people can imagine the voice of someone when they look at his or her face, we…

This paper introduces a new corpus of Mandarin-English code-switching speech recognition--TALCS corpus, suitable for training and evaluating code-switching speech recognition systems. TALCS corpus is derived from real online one-to-one…

With the development of deep learning, automatic speech recognition (ASR) has made significant progress. To further enhance the performance of ASR, revising recognition results is one of the lightweight but efficient manners. Various…

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for…

Lecture transcript translation helps learners understand online courses, however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel…

Limited availability of multilingual text corpora for training language models often leads to poor performance on downstream tasks due to undertrained representation spaces for languages other than English. This 'under-representation' has…

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…

The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper…