相关论文: Sylber 2.0: A Universal Syllable Embedding

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually…

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow…

Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into…

Speaker-adaptive Text-to-Speech (TTS) synthesis has attracted considerable attention due to its broad range of applications, such as personalized voice assistant services. While several approaches have been proposed, they often exhibit high…

Real-time voice conversion and speaker anonymization require causal, low-latency synthesis without sacrificing intelligibility or naturalness. Current systems have a core representational mismatch: content is time-varying, while speaker…

In this paper, we propose a novel Lip-to-Speech synthesis (L2S) framework, for synthesizing intelligible speech from a silent lip movement video. Specifically, to complement the insufficient supervisory signal of the previous L2S model, we…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

A Spoken dialogue system for an unseen language is referred to as Zero resource speech. It is especially beneficial for developing applications for languages that have low digital resources. Zero resource speech synthesis is the task of…

This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. We take a Machine Translation (MT) inspired approach to constructing the…

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…

Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is…

Textless spoken language models (SLMs) are generative models of speech that do not rely on text supervision. Most textless SLMs learn to predict the next semantic token, a discrete representation of linguistic content, and rely on a…

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…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art…

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…

In this paper, we explore the untapped potential of Whisper, a well-established automatic speech recognition (ASR) foundation model, in the context of L2 spoken language assessment (SLA). Unlike prior studies that extrinsically analyze…

In this paper, we propose a model to perform style transfer of speech to singing voice. Contrary to the previous signal processing-based methods, which require high-quality singing templates or phoneme synchronization, we explore a…