相关论文: WenetSpeech-Wu: Datasets, Benchmarks, and Models f…

The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce…

With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we present WenetSpeech4TTS, a multi-domain Mandarin corpus…

The development of speech understanding and generation has been significantly accelerated by the availability of large-scale, high-quality speech datasets. Among these, ASR and TTS are regarded as the most established and fundamental tasks.…

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect…

We introduce a FLORES+ dataset as an evaluation benchmark for modern Wu Chinese machine translation models and showcase its compatibility with existing Wu data. Wu Chinese is mutually unintelligible with other Sinitic languages such as…

Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress…

The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what extent can low error rates on academic benchmarks translate…

Multimodal Large Language Models (MLLMs) process visual, acoustic, and textual inputs, addressing the limitations of single-modality LLMs. However, existing benchmarks often overlook tri-modal evaluation in Traditional Chinese and do not…

The evaluation of large language models is an essential task in the field of language understanding and generation. As language models continue to advance, the need for effective benchmarks to assess their performance has become imperative.…

Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to generate a more emotional and more expressive speech is…

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in…

This paper presents BSTC (Baidu Speech Translation Corpus), a large-scale Chinese-English speech translation dataset. This dataset is constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of…

The advancements of neural dialogue generation models show promising results on modeling short-text conversations. However, training such models usually needs a large-scale high-quality dialogue corpus, which is hard to access. In this…

Large-scale text-to-speech (TTS) models have made significant progress recently.However, they still fall short in the generation of Chinese dialectal speech. Toaddress this, we propose Bailing-TTS, a family of large-scale TTS models capable…

Tibetan text-to-speech (TTS) has long been challenged by scarce speech resources, significant dialectal variation, and the complex mapping between written text and spoken pronunciation. To address these issues, this work presents, to the…

Full-duplex, spontaneous conversational data are essential for enhancing the naturalness and interactivity of synthesized speech in conversational TTS systems. We present two open-source dual-track conversational speech datasets, one in…

Despite the growing reliance on fairness benchmarks to evaluate language models, the datasets that underpin these benchmarks remain critically underexamined. This survey addresses that overlooked foundation by offering a comprehensive…

The development of high-performance, on-device keyword spotting (KWS) systems for ultra-low-power hardware is critically constrained by the scarcity of specialized, multi-command training datasets. Traditional data collection through human…

Recently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs). However, the use of in-the-wild large-scale speech data in the speech technology community…

Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity,…