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 . |
Similar Papers
In-the-wild Audio Spatialization with Flexible Text-guided Localization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for mapping monaural audio to binaural signals lack flexibility and interactive control needed in complex multi-object user-interactive environments. |
| Approach: | They propose a text-guided audio spatialization framework that utilizes diverse text prompts to evaluate binaural audio models. |
| Outcome: | The proposed framework learns binaural differences guided by 3D spatial location and relative position prompts, enhanced with flipped-channel audio. |
Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units (2023.findings-emnlp)
Copied to clipboard
| Challenge: | DISSC is a lightweight voice conversion method that converts the rhythm, pitch contour and timbre of a recording to a target speaker in a textless manner. |
| Approach: | They propose a method that converts rhythm, pitch contour and timbre of a recording to a target speaker in a textless manner. |
| Outcome: | The proposed method outperforms baseline methods on quantitative and qualitative evaluations. |
Fine-grained Artificial Neurons in Audio-transformers for Disentangling Neural Auditory Encoding (2023.findings-acl)
Copied to clipboard
Mengyue Zhou, Xu Liu, David Liu, Zihao Wu, Zhengliang Liu, Lin Zhao, Dajiang Zhu, Lei Guo, Junwei Han, Tianming Liu, Xintao Hu
| Challenge: | Existing studies treat each transformer encoding layer as a single artificial neuron . layer-level embeddings aggregate multiple types of contextual attention captured by multiple head modules . |
| Approach: | They propose to embed each transformer encoding layer as a single artificial neuron . they propose to couple those ANs with their biological-neuron counterparts in the human brain . |
| Outcome: | The proposed models can be used to link representations to brain activity, the authors say . their results show that the proposed models carry meaningful neurolinguistic information . |
Learning When to Translate for Streaming Speech (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods waiting-and-translating for a fixed duration break speech acoustic units . Existing models waiting-for a set duration and generating partial sentences are not effective . |
| Approach: | They propose a monotonic segmentation module inside an encoder-decoder model to detect proper speech unit boundaries for a streaming speech input. |
| Outcome: | The proposed method outperforms existing methods on a speech translation dataset and achieves the best trade-off between translation quality and latency. |
A Manually Annotated Resource for the Investigation of Nasal Grunts (2020.lrec-1)
Copied to clipboard
| Challenge: | acoustic annotation of nasal grunts is described in the whole CID corpus of the french language . acculturation of non-lexical conversational sounds has been debated for a long time . |
| Approach: | They propose an annotation framework for nasal grunts of the whole French CID corpus . they characterise acoustic cues and visual cue conventions followed for the annotation . |
| Outcome: | The proposed framework is based on the entire French CID corpus. |
Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model (2024.emnlp-main)
Copied to clipboard
Xiangyu Zhang, Daijiao Liu, Hexin Liu, Qiquan Zhang, Hanyu Meng, Leibny Paola Garcia Perera, EngSiong Chng, Lina Yao
| Challenge: | Existing approaches to enhance inference speed and training require complex modifications to the model. |
| Approach: | They propose to double the training and inference speed of Denoising Diffusion Probabilistic Models by simply redirecting the generative target to the wavelet domain. |
| Outcome: | The proposed method doubles the training and inference speed of Speech DDPMs by redirecting the generative target to the wavelet domain. |
DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility (2025.findings-naacl)
Copied to clipboard
| Challenge: | Video-to-speech (V2S) synthesis requires acoustic hints to accurately reconstruct both speech content and speaker characteristics from video clips alone. |
| Approach: | They propose a video-to-speech (V2S) model that predicts Mel-spectrograms directly from video frames. |
| Outcome: | The proposed model outperforms existing models in acoustic intelligibility and preserves speaker-specific characteristics. |
DNN-based Speech Synthesis Using Abundant Tags of Spontaneous Speech Corpus (2020.lrec-1)
Copied to clipboard
Yuki Yamashita, Tomoki Koriyama, Yuki Saito, Shinnosuke Takamichi, Yusuke Ijima, Ryo Masumura, Hiroshi Saruwatari
| Challenge: | Experimental evaluation results show that rich annotations enhance the reproducibility of paralinguistic features of synthetic speech. |
| Approach: | They investigate the effectiveness of using rich annotations in deep neural network-based statistical speech synthesis. |
| Outcome: | The proposed method improves reproducibility of paralinguistic features of synthetic speech . the corpus of spontaneous Japanese (CSJ) has large annotations on paralinguistic and nonlinguistic features . |
SBAAM! Eliminating Transcript Dependency in Automatic Subtitling (2024.acl-long)
Copied to clipboard
| Challenge: | Subtitling is a crucial task for enhancing the accessibility of audiovisual content and relying on automatic transcripts for the three subtasks is uncharted territory. |
| Approach: | They propose a model capable of producing automatic subtitles, completely eliminating any dependence on intermediate transcripts also for timestamp prediction. |
| Outcome: | Experimental results show that the proposed model eliminates the need for intermediate transcripts for timestamp prediction across multiple language pairs and diverse conditions. |
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. |