相关论文: Advancing NAM-to-Speech Conversion with Novel Meth…

Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform…

Large, human-annotated datasets are central to the development of natural language processing models. Collecting these datasets can be the most challenging part of the development process. We address this problem by introducing a general…

Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this…

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

While neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible for the vast majority of the world's…

Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unified models often suffer from large parameter sizes, making…

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization,…

Articulatory information has been shown to be effective in improving the performance of HMM-based and DNN-based text-to-speech synthesis. Speech synthesis research focuses traditionally on text-to-speech conversion, when the input is text…

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…

While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method…

Multi-speaker speech synthesis is a technique for modeling multiple speakers' voices with a single model. Although many approaches using deep neural networks (DNNs) have been proposed, DNNs are prone to overfitting when the amount of…

We introduce SMALLTALK LM, an innovative method for training a mixture of language models in an almost asynchronous manner. Each model of the mixture specializes in distinct parts of the data distribution, without the need for…

Recent efforts target spoken language models (SLMs) that not only listen but also speak for more natural human-LLM interaction. Joint speech-text modeling is a promising direction to achieve this. However, the effectiveness of recent speech…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

Disentanglement of a speaker's timbre and style is very important for style transfer in multi-speaker multi-style text-to-speech (TTS) scenarios. With the disentanglement of timbres and styles, TTS systems could synthesize expressive speech…

The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this…

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…

Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition. Robustness of distant speech recognition in adverse acoustic…

With read-aloud speech synthesis achieving high naturalness scores, there is a growing research interest in synthesising spontaneous speech. However, human spontaneous face-to-face conversation has both spoken and non-verbal aspects (here,…