Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP

• URL: http://arxiv.org/abs/2409.02451v1
• Date: Wed, 4 Sep 2024 05:12:15 GMT
• Title: Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP
• Abstract summary: Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter. We propose a fast, high-quality, and parameter-efficientP articulatory vocoder that can synthesize speech from EMA, F0, and loudness. Our model achieves a transcription word error rate (WER) of 6.67% and a mean opinion score (MOS) of 3.74, with an improvement of 1.63% and 0.16 compared to the state-of-the-art (SOTA) baseline.
• Score: 6.295981052578859
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded features for speech synthesis. Differentiable digital signal processing (DDSP) is a parameter-efficient framework for audio synthesis. Therefore, integrating low-dimensional EMA features with DDSP can significantly enhance the computational efficiency of speech synthesis. In this paper, we propose a fast, high-quality, and parameter-efficient DDSP articulatory vocoder that can synthesize speech from EMA, F0, and loudness. We incorporate several techniques to solve the harmonics / noise imbalance problem, and add a multi-resolution adversarial loss for better synthesis quality. Our model achieves a transcription word error rate (WER) of 6.67% and a mean opinion score (MOS) of 3.74, with an improvement of 1.63% and 0.16 compared to the state-of-the-art (SOTA) baseline. Our DDSP vocoder is 4.9x faster than the baseline on CPU during inference, and can generate speech of comparable quality with only 0.4M parameters, in contrast to the 9M parameters required by the SOTA.

Related papers

• The Talking Robot: Distortion-Robust Acoustic Models for Robot-Robot Communication [6.356219992638542]
  Artoo is a learned acoustic communication system for robots.<n>It replaces hand-designed signal processing with end-to-end co-trained neural networks.
  arXiv  Detail & Related papers  (2026-03-07T07:06:41Z)
• RT-VC: Real-Time Zero-Shot Voice Conversion with Speech Articulatory Coding [1.6012334795166434]
  RT-VC is a zero-shot real-time voice conversion system that delivers ultra-low latency and high-quality performance.<n>We show that RT-VC achieves a CPU latency of 61.4 ms, representing a 13.3% reduction in latency.
  arXiv  Detail & Related papers  (2025-06-12T02:02:38Z)
• Ultra-lightweight Neural Differential DSP Vocoder For High Quality Speech Synthesis [9.916195285279931]
  A DSP vocoder often gets a lower audio quality due to consuming over-smoothed acoustic model predictions. We propose an ultra-lightweight DSP (DDSP) vocoder that uses a jointly optimized acoustic model with a DSP vocoder, and learns without an extracted spectral feature for the vocal tract.
  arXiv  Detail & Related papers  (2024-01-19T02:51:00Z)
• A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS [52.51848317549301]
  We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data. In synthesis, the neural vocoder converts the predicted MSMCRs into final speech waveforms.
  arXiv  Detail & Related papers  (2022-09-22T09:43:17Z)
• DDX7: Differentiable FM Synthesis of Musical Instrument Sounds [7.829520196474829]
  Differentiable Digital Signal Processing (DDSP) has enabled nuanced audio rendering by Deep Neural Networks (DNNs) We present Differentiable DX7 (DDX7), a lightweight architecture for neural FM resynthesis of musical instrument sounds.
  arXiv  Detail & Related papers  (2022-08-12T08:39:45Z)
• Adding Connectionist Temporal Summarization into Conformer to Improve Its Decoder Efficiency For Speech Recognition [22.61761934996406]
  We propose a novel connectionist temporal summarization (CTS) method that reduces the number of frames required for the attention decoder. With a beamwidth of 4, the LibriSpeech's decoding budget can be reduced by up to 20%. The word error rate (WER) is reduced by 6% relative at the beam width of 1 and by 3% relative at the beam width of 4.
  arXiv  Detail & Related papers  (2022-04-08T07:24:00Z)
• NeuralDPS: Neural Deterministic Plus Stochastic Model with Multiband Excitation for Noise-Controllable Waveform Generation [67.96138567288197]
  We propose a novel neural vocoder named NeuralDPS which can retain high speech quality and acquire high synthesis efficiency and noise controllability. It generates waveforms at least 280 times faster than the WaveNet vocoder. It is also 28% faster than WaveGAN's synthesis efficiency on a single core.
  arXiv  Detail & Related papers  (2022-03-05T08:15:29Z)
• Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds [29.012177604120048]
  A differentiable digital signal processing (DDSP) autoencoder is a musical sound that combines a deep neural network (DNN) and spectral modeling synthesis. It allows us to flexibly edit sounds by changing the fundamental frequency, timbre feature, and loudness (synthesis parameters) extracted from an input sound. It is designed for a monophonic harmonic sound and cannot handle mixtures of sounds harmonic.
  arXiv  Detail & Related papers  (2022-02-01T03:38:49Z)
• Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers [56.56220390953412]
  We extend our prior work by introducing the Conformer architecture to further improve the accuracy. We demonstrate that the extended Transformer provides state-of-the-art end-to-end ASR performance.
  arXiv  Detail & Related papers  (2021-04-19T16:18:00Z)
• You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation [59.31769998728787]
  We build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. Our system establishes a competitive result for end-to-end ASR trained on LibriSpeech train-clean-100 set with WER 4.3% for test-clean and 13.5% for test-other.
  arXiv  Detail & Related papers  (2020-05-14T17:24:57Z)
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription [73.66530509749305]
  In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
  arXiv  Detail & Related papers  (2020-04-22T19:08:33Z)
• VaPar Synth -- A Variational Parametric Model for Audio Synthesis [78.3405844354125]
  We present VaPar Synth - a Variational Parametric Synthesizer which utilizes a conditional variational autoencoder (CVAE) trained on a suitable parametric representation. We demonstrate our proposed model's capabilities via the reconstruction and generation of instrumental tones with flexible control over their pitch.
  arXiv  Detail & Related papers  (2020-03-30T16:05:47Z)

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.