Search Results for author:
Found 47 papers, 28 papers with code
Scaling Transformers for Low-Bitrate High-Quality Speech Coding
The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context.
Learning Source Disentanglement in Neural Audio Codec
Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens.
Universal Sound Separation with Self-Supervised Audio Masked Autoencoder
In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance.
Learning Retrieval Augmentation for Personalized Dialogue Generation
Specifically, the proposed LAPDOG model consists of a story retriever and a dialogue generator.
Selective Prompting Tuning for Personalized Conversations with LLMs
To alleviate those issues, we propose \textbf{S}elective \textbf{P}rompt \textbf{T}uning (SPT), which softly prompts LLMs for personalized conversations in a selective way.
Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Review
This paper presents a comprehensive review of three interconnected digital aquaculture tasks, namely, fish tracking, counting, and behaviour analysis, using a novel and unified approach.
Dynamic Identity-Guided Attention Network for Visible-Infrared Person Re-identification
Effectively minimizing these cross-modal discrepancies relies on obtaining representations that are guided by identity and consistent across modalities, while also filtering out representations that are irrelevant to identity.
ComposerX: Multi-Agent Symbolic Music Composition with LLMs
Music composition represents the creative side of humanity, and itself is a complex task that requires abilities to understand and generate information with long dependency and harmony constraints.
T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining
Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks.
WavCraft: Audio Editing and Generation with Large Language Models
We introduce WavCraft, a collective system that leverages large language models (LLMs) to connect diverse task-specific models for audio content creation and editing.
Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
Moreover, we improve the framework of audio language model by using interleaved audio-text embeddings as the input sequence.
Audio Prompt Tuning for Universal Sound Separation
Specifically, APT improves the separation performance of specific sources through training a small number of prompt parameters with limited audio samples, while maintaining the generalization of the USS model by keeping its parameters frozen.
CM-PIE: Cross-modal perception for interactive-enhanced audio-visual video parsing
Audio-visual video parsing is the task of categorizing a video at the segment level with weak labels, and predicting them as audible or visible events.
Retrieval-Augmented Text-to-Audio Generation
Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance.
Ranked #3 on
Audio Generation
on AudioCaps
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining
Any audio can be translated into LOA based on AudioMAE, a self-supervised pre-trained representation learning model.
Ranked #4 on
Audio Generation
on AudioCaps
Separate Anything You Describe
In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries.
WavJourney: Compositional Audio Creation with Large Language Models
Subjective evaluations demonstrate the potential of WavJourney in crafting engaging storytelling audio content from text.
Text-Driven Foley Sound Generation With Latent Diffusion Model
We have observed that the feature embedding extracted by the text encoder can significantly affect the performance of the generation model.
Knowledge Distillation for Efficient Audio-Visual Video Captioning
Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields.
Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning
Experimental results show that LHDFF outperforms existing audio captioning models.
Adapting Language-Audio Models as Few-Shot Audio Learners
We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data.
SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision
Furthermore, when combined with large-scale pseudo-labeled audio-visual data SynthVSR yields a new state-of-the-art VSR WER of 16. 9% using publicly available data only, surpassing the recent state-of-the-art approaches trained with 29 times more non-public machine-transcribed video data (90, 000 hours).
Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Study
Deep neural networks have recently achieved breakthroughs in sound generation.
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency.
Ranked #10 on
Audio Generation
on AudioCaps
Towards Generating Diverse Audio Captions via Adversarial Training
Captions generated by existing models are generally faithful to the content of audio clips, however, these machine-generated captions are often deterministic (e. g., generating a fixed caption for a given audio clip), simple (e. g., using common words and simple grammar), and generic (e. g., generating the same caption for similar audio clips).
Ontology-aware Learning and Evaluation for Audio Tagging
The proposed metric, ontology-aware mean average precision (OmAP) addresses the weaknesses of mAP by utilizing the AudioSet ontology information during the evaluation.
Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention
Audio captioning aims to generate text descriptions of audio clips.
Personalized Dialogue Generation with Persona-Adaptive Attention
Persona-based dialogue systems aim to generate consistent responses based on historical context and predefined persona.
Automated Audio Captioning via Fusion of Low- and High- Dimensional Features
Moreover, in LHDFF, a new PANNs encoder is proposed called Residual PANNs (RPANNs) by fusing the low-dimensional feature from the intermediate convolution layer output and the high-dimensional feature from the final layer output of PANNs.
Learning Temporal Resolution in Spectrogram for Audio Classification
The audio spectrogram is a time-frequency representation that has been widely used for audio classification.
Simple Pooling Front-ends For Efficient Audio Classification
Recently, there has been increasing interest in building efficient audio neural networks for on-device scenarios.
Low-complexity CNNs for Acoustic Scene Classification
This technical report describes the SurreyAudioTeam22s submission for DCASE 2022 ASC Task 1, Low-Complexity Acoustic Scene Classification (ASC).
Segment-level Metric Learning for Few-shot Bioacoustic Event Detection
In addition, we use transductive inference on the validation set during training for better adaptation to novel classes.
Continual Learning For On-Device Environmental Sound Classification
Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification.
Automated Audio Captioning: An Overview of Recent Progress and New Challenges
In this paper, we present a comprehensive review of the published contributions in automated audio captioning, from a variety of existing approaches to evaluation metrics and datasets.
VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration
Speech restoration aims to remove distortions in speech signals.
On Metric Learning for Audio-Text Cross-Modal Retrieval
We present an extensive evaluation of popular metric learning objectives on the AudioCaps and Clotho datasets.
Neural Vocoder is All You Need for Speech Super-resolution
In this paper, we propose a neural vocoder based speech super-resolution method (NVSR) that can handle a variety of input resolution and upsampling ratios.
Ranked #2 on
Audio Super-Resolution
on VCTK Multi-Speaker
Separate What You Describe: Language-Queried Audio Source Separation
In this paper, we introduce the task of language-queried audio source separation (LASS), which aims to separate a target source from an audio mixture based on a natural language query of the target source (e. g., "a man tells a joke followed by people laughing").
Deep Neural Decision Forest for Acoustic Scene Classification
In this paper, we propose a novel approach for ASC using deep neural decision forest (DNDF).
Leveraging Pre-trained BERT for Audio Captioning
BERT is a pre-trained language model that has been extensively used in Natural Language Processing (NLP) tasks.
Diverse Audio Captioning via Adversarial Training
As different people may describe an audio clip from different aspects using distinct words and grammars, we argue that an audio captioning system should have the ability to generate diverse captions for a fixed audio clip and across similar audio clips.
An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning
Automated audio captioning aims to use natural language to describe the content of audio data.
CL4AC: A Contrastive Loss for Audio Captioning
Automated Audio captioning (AAC) is a cross-modal translation task that aims to use natural language to describe the content of an audio clip.
Audio Captioning Transformer
In this paper, we propose an Audio Captioning Transformer (ACT), which is a full Transformer network based on an encoder-decoder architecture and is totally convolution-free.
Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning
We evaluate our approach on the UrbanSound8K dataset, compared to SampleRNN, with the performance metrics measuring the quality and diversity of generated sounds.
Token-Level Supervised Contrastive Learning for Punctuation Restoration
Punctuation is critical in understanding natural language text.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
