Related papers: Phonological Tokenizer: Prosody-Aware Phonetic Tok…

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is continuous and complex, it is often discretized for autoregressive modeling. Speech tokens derived from…

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

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,…

Prior research has demonstrated noticeable performance gains through the use of probabilistic tokenizations, an approach that involves employing multiple tokenizations of the same input string during the training phase of a language model.…

Multilingual spoken dialogue systems have gained prominence in the recent past necessitating the requirement for a front-end Language Identification (LID) system. Most of the existing LID systems rely on modeling the language discriminative…

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…

Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts…

Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information.…

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Spoof diarization identifies ``what spoofed when" in a given speech by temporally locating spoofed regions and determining their manipulation techniques. As a first step toward this task, prior work proposed a two-branch model for…

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…

Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech…

Prosody plays a crucial role in speech perception, influencing both human understanding and automatic speech recognition (ASR) systems. Despite its importance, prosodic stress remains under-studied due to the challenge of efficiently…

Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…

Prosody modeling is important, but still challenging in expressive voice conversion. As prosody is difficult to model, and other factors, e.g., speaker, environment and content, which are entangled with prosody in speech, should be removed…

Prosody Transfer (PT) is a technique that aims to use the prosody from a source audio as a reference while synthesising speech. Fine-grained PT aims at capturing prosodic aspects like rhythm, emphasis, melody, duration, and loudness, from a…