相关论文: Single-stage TTS with Masked Audio Token Modeling …

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discretized into token…

Speech emotion recognition (SER) performance deteriorates significantly in the presence of noise, making it challenging to achieve competitive performance in noisy conditions. To this end, we propose a multi-level knowledge distillation…

Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global…

Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher…

While recent zero-shot multi-speaker text-to-speech (TTS) models achieve impressive results, they typically rely on extensive transcribed speech datasets from numerous speakers and intricate training pipelines. Meanwhile, self-supervised…

We propose Guided-TTS, a high-quality text-to-speech (TTS) model that does not require any transcript of target speaker using classifier guidance. Guided-TTS combines an unconditional diffusion probabilistic model with a separately trained…

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…

Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality…

There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory…

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…

Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant compatibility challenges. Typically,…

Knowledge distillation is a powerful technique for transferring knowledge from a pre-trained teacher model to a student model. However, the true potential of knowledge transfer has not been fully explored. Existing approaches primarily…

Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering…

It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each…

Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer architecture, processing these long token streams with…

Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding. A unified model is desirable for applications that require…

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…

We present a neural text-to-speech (TTS) method that models natural vocal effort variation to improve the intelligibility of synthetic speech in the presence of noise. The method consists of first measuring the spectral tilt of unlabeled…

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…