相关论文: Speech Token Prediction via Compressed-to-fine Lan…

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models…

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…

Neural audio codecs are foundational to speech language models. It is expected to have a low frame rate and decoupled semantic and acoustic information. A lower frame rate codec can reduce the computational cost of speech language models by…

Speech codecs are traditionally optimized for waveform fidelity, allocating bits to preserve acoustic detail even when much of it can be inferred from linguistic structure. This leads to inefficient compression and suboptimal performance on…

Discrete Audio codecs (or audio tokenizers) have recently regained interest due to the ability of Large Language Models (LLMs) to learn their compressed acoustic representations. Various publicly available trainable discrete tokenizers…

Neural audio codecs provide compact discrete representations for speech generation and manipulation. However, most codecs organize tokens as frame-level sequences, making it difficult to study or intervene on global factors of variation. In…

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…

We consider the generative modeling of speech over multiple minutes, a requirement for long-form multimedia generation and audio-native voice assistants. However, textless spoken language models struggle to generate plausible speech past…

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to adapt them to low-latency scenarios. In this paper, we…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural…

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Speech perception involves storing and integrating sequentially presented items. Recent work in cognitive neuroscience has identified temporal and contextual characteristics in humans' neural encoding of speech that may facilitate this…

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates…

Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in…