Efficient Autoregressive Audio Modeling via Next-Scale Prediction

• URL: http://arxiv.org/abs/2408.09027v1
• Date: Fri, 16 Aug 2024 21:48:53 GMT
• Title: Efficient Autoregressive Audio Modeling via Next-Scale Prediction
• Authors: Kai Qiu, Xiang Li, Hao Chen, Jie Sun, Jinglu Wang, Zhe Lin, Marios Savvides, Bhiksha Raj,
• Abstract summary: We analyze the token length of audio tokenization and propose a novel textbfScale-level textbfAudio textbfTokenizer (SAT) Based on SAT, a scale-level textbfAcoustic textbfAutotextbfRegressive (AAR) modeling framework is proposed, which shifts the next-token AR prediction to next-scale AR prediction.
• Score: 52.663934477127405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the efficiency of audio generation remains an essential issue to be addressed, especially for AR models that are incorporated in large language models (LLMs). In this paper, we analyze the token length of audio tokenization and propose a novel \textbf{S}cale-level \textbf{A}udio \textbf{T}okenizer (SAT), with improved residual quantization. Based on SAT, a scale-level \textbf{A}coustic \textbf{A}uto\textbf{R}egressive (AAR) modeling framework is further proposed, which shifts the next-token AR prediction to next-scale AR prediction, significantly reducing the training cost and inference time. To validate the effectiveness of the proposed approach, we comprehensively analyze design choices and demonstrate the proposed AAR framework achieves a remarkable \textbf{35}$\times$ faster inference speed and +\textbf{1.33} Fr\'echet Audio Distance (FAD) against baselines on the AudioSet benchmark. Code: \url{https://github.com/qiuk2/AAR}.

Related papers

• Tailored Design of Audio-Visual Speech Recognition Models using Branchformers [0.0]
  We propose a novel framework for the design of parameter-efficient Audio-Visual Speech Recognition systems. To be more precise, the proposed framework consists of two steps: first, estimating audio- and video-only systems, and then designing a tailored audio-visual unified encoder. Results reflect how our tailored AVSR system is able to reach state-of-the-art recognition rates.
  arXiv  Detail & Related papers  (2024-07-09T07:15:56Z)
• VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment [101.2489492032816]
  VALL-E R is a robust and efficient zero-shot Text-to-Speech system. This research has the potential to be applied to meaningful projects, including the creation of speech for those affected by aphasia.
  arXiv  Detail & Related papers  (2024-06-12T04:09:44Z)
• An Experimental Study: Assessing the Combined Framework of WavLM and BEST-RQ for Text-to-Speech Synthesis [0.5076419064097734]
  We propose a new model architecture specifically suited for text-to-speech (TTS) models. We combine WavLM, a pre-trained self-supervised learning (SSL) speech model, and the BEST-RQ vector quantization framework. Experiments on the LibriSpeech dataset with SUPERB benchmarking assert that the proposed model significantly underperforms.
  arXiv  Detail & Related papers  (2023-12-08T23:59:25Z)
• High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models [56.00939852727501]
  Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations. Non-autoregressive framework enhances controllability, and duration diffusion model enables diversified prosodic expression.
  arXiv  Detail & Related papers  (2023-09-27T09:27:03Z)
• Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition [13.53738829631595]
  We propose a novel method to extract the denoising capabilities, that can be applied to any encoder-decoder architecture. We train our pre-processor on the Noisy Speech Database (NSD) to reconstruct denoised spectrograms from noisy inputs. We show that the Cleancoder is able to filter noise from speech and that it improves the total Word Error Rate (WER) of the downstream model in noisy conditions.
  arXiv  Detail & Related papers  (2023-09-05T11:34:21Z)
• Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding [57.42429912884543]
  We propose Diff-LM-Speech, Tetra-Diff-Speech and Tri-Diff-Speech to solve high dimensionality and waveform distortion problems. We also introduce a prompt encoder structure based on a variational autoencoder and a prosody bottleneck to improve prompt representation ability. Experimental results show that our proposed methods outperform baseline methods.
  arXiv  Detail & Related papers  (2023-07-28T11:20:23Z)
• Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models [65.18102159618631]
  multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. We propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps.
  arXiv  Detail & Related papers  (2023-01-30T04:44:34Z)
• A Study on Speech Enhancement Based on Diffusion Probabilistic Model [63.38586161802788]
  We propose a diffusion probabilistic model-based speech enhancement model (DiffuSE) model that aims to recover clean speech signals from noisy signals. The experimental results show that DiffuSE yields performance that is comparable to related audio generative models on the standardized Voice Bank corpus task.
  arXiv  Detail & Related papers  (2021-07-25T19:23:18Z)
• Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition [9.732767611907068]
  In this work, we fuse a pre-trained acoustic encoder (wav2vec2.0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model. Our model achieves better recognition performance on CALLHOME corpus (15 hours) than other end-to-end models.
  arXiv  Detail & Related papers  (2021-01-17T16:12:44Z)
• Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings [42.17790794610591]
  An end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed recently to jointly perform speaker counting, speech recognition and speaker identification. The model achieved a low speaker-attributed word error rate (SA-WER) for monaural overlapped speech comprising an unknown number of speakers. It has yet to be investigated whether the E2E SA-ASR model works well for recordings that are much longer than samples seen during training.
  arXiv  Detail & Related papers  (2021-01-06T03:36:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.