Related papers: TCSinger 2: Customizable Multilingual Zero-shot Si…

The speech domain prevails in the spotlight for several natural language processing (NLP) tasks while the singing domain remains less explored. The culmination of NLP is the speech-to-speech translation (S2ST) task, referring to translation…

Code-switching---the intra-utterance use of multiple languages---is prevalent across the world. Within text-to-speech (TTS), multilingual models have been found to enable code-switching. By modifying the linguistic input to…

Singing voice synthesis (SVS) has seen remarkable advancements in recent years. However, compared to speech and general audio data, publicly available singing datasets remain limited. In practice, this data scarcity often leads to…

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer…

Recently, zero-shot text-to-speech (TTS) systems, capable of synthesizing any speaker's voice from a short audio prompt, have made rapid advancements. However, the quality of the generated speech significantly deteriorates when the audio…

Automatic transcription of monophonic/polyphonic music is a challenging task due to the lack of availability of large amounts of transcribed data. In this paper, we propose a data augmentation method that converts natural speech to singing…

Singing voice synthesis (SVS) aims to generate natural and expressive singing waveforms from symbolic musical scores. In cVAE-based SVS, however, a mismatch arises because the decoder is trained with latent representations inferred from…

Incorporating cross-speaker style transfer in text-to-speech (TTS) models is challenging due to the need to disentangle speaker and style information in audio. In low-resource expressive data scenarios, voice conversion (VC) can generate…

In this paper, we propose a singing voice synthesis model, Karaoker-SSL, that is trained only on text and speech data as a typical multi-speaker acoustic model. It is a low-resource pipeline that does not utilize any singing data…

Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate…

Direct speech-to-speech translation (S2ST) has gradually become popular as it has many advantages compared with cascade S2ST. However, current research mainly focuses on the accuracy of semantic translation and ignores the speech style…

Singing voice conversion (SVC) aims to render the target singer's timbre while preserving melody and lyrics. However, existing zero-shot SVC systems remain fragile in real songs due to harmony interference, F0 errors, and the lack of…

This research presents Muskits-ESPnet, a versatile toolkit that introduces new paradigms to Singing Voice Synthesis (SVS) through the application of pretrained audio models in both continuous and discrete approaches. Specifically, we…

Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work…

Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently, by using a well-trained source TTS model without adapting it on the speech data of new speakers. Considering seen and unseen speakers have diverse…

Speech Language Models (SLMs) have recently emerged as a unified paradigm for addressing a wide range of speech-related tasks, including text-to-speech (TTS), speech enhancement (SE), and automatic speech recognition (ASR). However, the…

We present the gradual style adaptor TTS (GSA-TTS) with a novel style encoder that gradually encodes speaking styles from an acoustic reference for zero-shot speech synthesis. GSA first captures the local style of each semantic sound unit.…

In this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two…

State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data, standard TTS models suffer from speech quality and…

Spontaneous speaking style exhibits notable differences from other speaking styles due to various spontaneous phenomena (e.g., filled pauses, prolongation) and substantial prosody variation (e.g., diverse pitch and duration variation,…