相关论文: Iterate to Differentiate: Enhancing Discriminabili…

The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time factor (RTF), and latency. In this paper, we present U2++, an…

Test-time scaling (TTS) aims to achieve better results by increasing random sampling and evaluating samples based on rules and metrics. However, in text-to-image(T2I) diffusion models, most related works focus on search strategies and…

We present LongCat-AudioDiT, a novel, non-autoregressive diffusion-based text-to-speech (TTS) model that achieves state-of-the-art (SOTA) performance. Unlike previous methods that rely on intermediate acoustic representations such as…

Community-driven Text-to-SQL evaluation platforms play a pivotal role in tracking the state of the art of Text-to-SQL performance. The reliability of the evaluation process is critical for driving progress in the field. Current evaluation…

Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate…

We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models…

In debating, rebuttal is one of the most critical stages, where a speaker addresses the arguments presented by the opposing side. During this process, the speaker synthesizes their own persuasive articulation given the context from the…

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with…

This paper introduces a novel framework for distributed two-sample testing using the Integrated Transportation Distance (ITD), an extension of the Optimal Transport distance. The approach addresses the challenges of detecting distributional…

Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference…

Text-to-Speech (TTS) synthesis using deep learning relies on voice quality. Modern TTS models are advanced, but they need large amount of data. Given the growing computational complexity of these models and the scarcity of large,…

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the…

Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive…

Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Zero-shot object counting aims to count instances of arbitrary object categories specified by text descriptions. Existing methods typically rely on vision-language models like CLIP, but often exhibit limited sensitivity to text prompts. We…

Second language (L2) learners can improve their pronunciation by imitating golden speech, especially when the speech that aligns with their respective speech characteristics. This study explores the hypothesis that learner-specific golden…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Readability-controlled text simplification (RCTS) rewrites texts to lower readability levels while preserving their meaning. RCTS models often depend on parallel corpora with readability annotations on both source and target sides. Such…

The goal of this paper is to introduce SPADE, a framework for Structured Pruning and Adaptive Distillation for Efficient Large Language Model-based text-to-speech (LLM-TTS). Recent LLM-TTS systems achieve strong controllability and…