38 citations · 206 across the 28 of their papers we have counts for
28 papers
Seedance 2.0: Advancing Video Generation for World Complexity
Team Seedance, De Chen, Liyang Chen +168
Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro…
Virtual Width Networks
Seed, Baisheng Li, Banggu Wu +115
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…
EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
Tianyu Guo, Hande Dong, Yichong Leng +4
Large language models (LLMs) are often used for infilling tasks, which involve predicting or generating missing information in a given text. These tasks typically require multiple…
Kimi-Audio Technical Report
KimiTeam, Ding Ding, Zeqian Ju +37
We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, inclu…
MoonCast: High-Quality Zero-Shot Podcast Generation
Zeqian Ju, Dongchao Yang, Jianwei Yu +7
Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for individual speakers. However, these systems still face cha…
Qwen2-Audio Technical Report
Yunfei Chu, Jin Xu, Qian Yang +9
We introduce the latest progress of Qwen-Audio, a large-scale audio-language model called Qwen2-Audio, which is capable of accepting various audio signal inputs and performing audi…
Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
Jingxuan Wei, Linzhuang Sun, Yichong Leng +3
Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or…
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Zeqian Ju, Yuancheng Wang, Kai Shen +16
While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intric…
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
Qian Yang, Jin Xu, Wenrui Liu +8
Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-cent…
PromptTTS 2: Describing and Generating Voices with Text Prompt
Yichong Leng, Zhifang Guo, Kai Shen +12
Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods rel…
Extract and Attend: Improving Entity Translation in Neural Machine Translation
Zixin Zeng, Rui Wang, Yichong Leng +4
While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, locatio…
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Kai Shen, Zeqian Ju, Xu Tan +6
Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, an…
Improving Code Search with Hard Negative Sampling Based on Fine-tuning
Hande Dong, Jiayi Lin, Yanlin Wang +3
Pre-trained code models have emerged as the state-of-the-art paradigm for code search tasks. The paradigm involves pre-training the model on search-irrelevant tasks such as masked…
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Zehua Chen, Yihan Wu, Yichong Leng +9
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, the…
SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition
Yichong Leng, Xu Tan, Wenjie Liu +6
Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word err…
Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
Kai Shen, Yichong Leng, Xu Tan +4
Text error correction aims to correct the errors in text sequences such as those typed by humans or generated by speech recognition models. Previous error correction methods usuall…
PromptTTS: Controllable Text-to-Speech with Text Descriptions
Zhifang Guo, Yichong Leng, Yihan Wu +2
Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this w…
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
Xu Tan, Jiawei Chen, Haohe Liu +11
Text to speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality…
BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
Yichong Leng, Zehua Chen, Junliang Guo +9
Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing the…
Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling
Kaitao Song, Yichong Leng, Xu Tan +3
Sentence scoring aims at measuring the likelihood score of a sentence and is widely used in many natural language processing scenarios, like reranking, which is to select the best…
A study on the efficacy of model pre-training in developing neural text-to-speech system
Guangyan Zhang, Yichong Leng, Daxin Tan +5
In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achie…
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Yichong Leng, Xu Tan, Rui Wang +8
Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple ca…
Analyzing and Mitigating Interference in Neural Architecture Search
Jin Xu, Xu Tan, Kaitao Song +5
Weight sharing is a popular approach to reduce the cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However…
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Yichong Leng, Xu Tan, Linchen Zhu +7
Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR…