Papers by Jinglin Liu

10 papers
SimulSpeech: End-to-End Simultaneous Speech to Text Translation (2020.acl-main)

Copied to clipboard

Challenge: SimulSpeech is an end-to-end simultaneous speech to text translation system . conventional approaches to simultaneous speech translation divide the translation process into two stages .
Approach: They develop an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently.
Outcome: The proposed system achieves reasonable BLEU scores and lower delay compared to full-sentence translation model.
RMSSinger: Realistic-Music-Score based Singing Voice Synthesis (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for singing voice synthesis are limited to fine-grained music scores . manual adjustment destroys regularity of note durations, making fine-grain music scores "crushed"
Approach: They propose a method to synthesize singing voices given realistic music scores . they use real-music-score-based Singing Voice Synthesis to generate high-quality voices .
Outcome: The proposed method eliminates manual annotation and simplifies phoneme-level mel-note alignment.
A Study of Non-autoregressive Model for Sequence Generation (2020.acl-main)

Copied to clipboard

Challenge: Non-autoregressive (NAR) models generate all tokens in parallel, resulting in faster generation speed compared to autoregressive models.
Approach: They propose to use knowledge distillation and source-target alignment to bridge the gap between NAR and autoregressive models in various tasks.
Outcome: The proposed techniques can speed up NAR models in some tasks but not all . the proposed techniques reduce target token dependency while allowing for faster inference .
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)

Copied to clipboard

Challenge: In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds.
Approach: They propose a method that leverages the overlap between context and model output to generate drafts from the context.
Outcome: The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks.
FastDiff 2: Revisiting and Incorporating GANs and Diffusion Models in High-Fidelity Speech Synthesis (2023.findings-acl)

Copied to clipboard

Challenge: Experimental results show that Generative adversarial networks sacrifice sample diversity for quality and speed, while diffusion models exhibit outperformed sample quality and diversity at a high computational cost.
Approach: They propose to combine GANs and diffusion probabilistic models to achieve better sample quality and diversity.
Outcome: The proposed models outperform GANs and diffusion models in speech synthesis . the proposed models enjoy an efficient 4-step sampling process and exhibit better sample diversity .
AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to speech-to-singing voice conversion are difficult to learn in text-free situations.
Approach: They propose an STS model which views speech variance as different modalities . it uses a novel rhythm adaptor to predict the target rhythm representation . they also use the predicted rhythm representation to re-align the content .
Outcome: The proposed model achieves superior performance in terms of objective and subjective metrics.
DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for binaural audio synthesis are limited in phase estimation, which is crucial for spatial hearing.
Approach: They propose a method to explicitly address the Doppler effect of the moving speaker . it calculates the radial relative velocity of the speaker in spherical coordinates .
Outcome: The proposed method improves the representative WarpNet and BinauralGrad backbones in phase error metric and reaches a new state of the art (SOTA) it is compared with the current method which is limited in phase estimation .
CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-Training (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for expressive text-to-speech only implicitly learn prosody with masked token reconstruction tasks.
Approach: They propose a cross-modal contrastive pre-training framework that learns from prosody variance of the same text token under different contexts.
Outcome: The proposed framework can learn from prosody variance of a text token under different contexts.
Learning the Beauty in Songs: Neural Singing Voice Beautifier (2022.acl-long)

Copied to clipboard

Challenge: Existing techniques for pitch correction are limited to intonation but ignore the overall aesthetic quality.
Approach: They propose a novel time-warping approach for pitch correction to synchronize the amateur recording with the template pitch curve.
Outcome: The proposed model improves intonation and vocal tone while keeping content and vocal timbre.
AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: Existing models for speech-to-speech translation suffer from distinct degradation in noisy environments and fail to translate visual speech.
Approach: They propose a text-based audio-visual speech-to-speech translation model that integrates visual information with audio-only data to improve system robustness.
Outcome: The proposed model outperforms models trained on audio-only corpus in two languages . it also improves with low-resource audio-visual data, compared with baselines .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations