3 citations · 6 across the 10 of their papers we have counts for
10 papers
WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
Jiangnan Yu, Kisson Songqi Lin, Jilong Wu
Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression or preserved but never retri…
GSRM: Generative Speech Reward Model for Speech RLHF
Maohao Shen, Tejas Jayashankar, Osama Hanna +10
Recent advances in speech language models, such as GPT-4o Voice Mode and Gemini Live, have demonstrated promising speech generation capabilities. Nevertheless, the aesthetic natura…
VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation
Yancheng Wang, Osama Hanna, Ruiming Xie +11
Emotion recognition in speech presents a complex multimodal challenge, requiring comprehension of both linguistic content and vocal expressivity, particularly prosodic features suc…
Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation
Maohao Shen, Shun Zhang, Jilong Wu +5
Large language models (LLMs) have revolutionized natural language processing (NLP) with impressive performance across various text-based tasks. However, the extension of text-domin…
Self-Supervised Representations for Singing Voice Conversion
Tejas Jayashankar, Jilong Wu, Leda Sari +3
A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio r…
Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition
Philipp Klumpp, Pooja Chitkara, Leda Sarı +5
The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for…
Voice-preserving Zero-shot Multiple Accent Conversion
Mumin Jin, Prashant Serai, Jilong Wu +3
Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent. For native speakers, understand…
Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders
Jason Fong, Yun Wang, Prabhav Agrawal +4
Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording. Recent work has used neural models to produce edi…
VocBench: A Neural Vocoder Benchmark for Speech Synthesis
Ehab A. AlBadawy, Andrew Gibiansky, Qing He +3
Neural vocoders, used for converting the spectral representations of an audio signal to the waveforms, are a commonly used component in speech synthesis pipelines. It focuses on sy…
Multi-rate attention architecture for fast streamable Text-to-speech spectrum modeling
Qing He, Zhiping Xiu, Thilo Koehler +1
Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates…