Related papers: The IMS Toucan System for the Blizzard Challenge 2…

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

The iDian (previously named as the Operation Agent System) is a framework designed to enable computer users to operate software in natural language. Distinct from current speech-recognition systems, our solution supports format-free…

BOUT++ is a 3D nonlinear finite-difference plasma simulation code, capable of solving quite general systems of PDEs, but targeted particularly on studies of the edge region of tokamak plasmas. BOUT++ is publicly available, and has been…

Despite recent progress in Natural Language Understanding (NLU), the creation of multilingual NLU systems remains a challenge. It is common to have NLU systems limited to a subset of languages due to lack of available data. They also often…

Currently, there are increasing interests in text-to-speech (TTS) synthesis to use sequence-to-sequence models with attention. These models are end-to-end meaning that they learn both co-articulation and duration properties directly from…

The ICASSP 2024 Speech Signal Improvement Grand Challenge is intended to stimulate research in the area of improving the speech signal quality in communication systems. This marks our second challenge, building upon the success from the…

Brain-to-speech (BTS) systems represent a groundbreaking approach to human communication by enabling the direct transformation of neural activity into linguistic expressions. While recent non-invasive BTS studies have largely focused on…

In this paper, we introduce a groundbreaking end-to-end (E2E) framework for decoding invasive brain signals, marking a significant advancement in the field of speech neuroprosthesis. Our methodology leverages the comprehensive reasoning…

Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over discrete units called tokens. To represent text, the vast majority of LLMs use words or word fragments as the…

Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations…

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Grapheme-to-phoneme (G2P) conversion is a crucial step in Text-to-Speech (TTS) systems, responsible for mapping grapheme to corresponding phonetic representations. However, it faces ambiguities problems where the same grapheme can represent…

Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes before assembling sentences with an n-gram…

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often…

Recently, the effectiveness of text-to-speech (TTS) systems combined with neural vocoders to generate high-fidelity speech has been shown. However, collecting the required training data and building these advanced systems from scratch are…

This research presents a novel framework integrating Flexible-Duplex (FlexD) and Integrated Sensing and Communications (ISAC) technologies to address the challenges of spectrum efficiency and resource optimization in next-generation…

Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS…

In this work, we present a novel perspective on cognitive impairment classification from speech by integrating speech foundation models that explicitly recognize speech dialects. Our motivation is based on the observation that individuals…

Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token…

Text-to-Image In-Context Learning (T2I-ICL) enables customized image synthesis via interleaved text-image examples but faces two mutually reinforcing bottlenecks, compliance failure and prior-dominated hallucination, that form a vicious…