Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations

Jing-Xuan Zhang, Zhen-Hua Ling, Li-Rong Dai

TL;DR

This paper introduces a novel method for non-parallel voice conversion (VC) that successfully disentangles linguistic content from speaker identity using a sequence-to-sequence (seq2seq) framework. By combining adversarial training with phoneme-level supervision, the model can transform a source speaker's voice into a target speaker's voice with high naturalness and similarity, even when the speakers haven't recorded the same sentences.

What Problem Does This Paper Address?

Voice Conversion (VC) is the task of changing the speaker identity of an utterance while keeping the underlying message intact. Traditionally, the most successful models required parallel data—recordings of different people saying the exact same sentences. In the real world, such datasets are rare and difficult to collect.

Non-parallel VC is much more practical but significantly harder. The primary challenge is "disentanglement": how do you separate what is being said (linguistics) from how it sounds (speaker identity)? Furthermore, most existing non-parallel methods operate frame-by-frame, meaning they cannot easily adjust the duration or prosody of speech. This paper aims to bridge the gap by bringing the flexibility of seq2seq modeling to the non-parallel VC domain.

Methods

The authors propose an encoder-decoder architecture designed to isolate speech components into distinct "spaces."

  1. Disentangled Representations:
    • Recognition Encoder ($E^r$): This component takes acoustic features and compresses them into a linguistic representation. It uses a "pyramid" BLSTM to reduce the time resolution, effectively mapping high-frequency audio frames to lower-frequency phoneme-like units.
  2. Text Encoder ($E^t$): During training, phoneme transcriptions are fed into this encoder. A contrastive loss is used to force the output of the Recognition Encoder (from audio) to match the output of the Text Encoder (from text), ensuring they share the same linguistic space.
  3. Adversarial Training: To ensure the linguistic representation is truly "speaker-blind," an auxiliary classifier ($C^s$) tries to guess the speaker's identity from it. The Recognition Encoder is trained to "fool" this classifier, effectively scrubbing away any residual speaker-specific information.
  4. Speaker Encoder ($E^s$): A separate network extracts a fixed embedding representing the target speaker's unique vocal characteristics.
  5. Seq2seq Decoding:
    • The Decoder ($D^a$) takes the "cleaned" linguistic embedding and the target speaker embedding to reconstruct the Mel-spectrogram. Because it is a seq2seq model with an attention mechanism, it can predict durations independently of the source audio.
  6. Two-Stage Training:
    • Pre-training: The model is first trained on a large, multi-speaker dataset to learn general speech representations.
  7. Fine-tuning: The model is then refined on a specific pair of source and target speakers to maximize conversion quality.

Datasets

  • VCTK: Used for pre-training. It contains 99 speakers and approximately 30 hours of speech.
  • CMU ARCTIC: Used for fine-tuning and evaluation. Specifically, the authors focused on the "slt" (female) and "rms" (male) speaker pair.
  • Benchmarks: The model was compared against CycleGAN-VC, the top-performing non-parallel method from the Voice Conversion Challenge 2018 (VCC2018), and a state-of-the-art parallel seq2seq model.

Key Insights and Ideas

  • The Power of Text Supervision: Even though the final conversion process doesn't require text input, using phoneme transcriptions during training acts as a "ground truth" for what linguistic information should look like. This prevents the model from getting lost in the high-dimensional complexity of raw audio.
  • Adversarial "Scrubbing": The authors found that phoneme supervision alone wasn't enough to remove speaker identity. The adversarial loss was the "aha moment" that successfully forced the encoder to ignore the speaker's tone and focus solely on the words.
  • Duration Modification: Unlike frame-by-frame models (like CycleGAN), this seq2seq approach can actually change the tempo of the speech. If a target speaker naturally speaks slower than the source, the model can learn to stretch the generated audio accordingly.

Key Results

  • Naturalness and Similarity: In subjective listening tests (Mean Opinion Score), the proposed method scored significantly higher than the VCC2018 winner. In fact, its performance was nearly indistinguishable from state-of-the-art models that do use parallel data.
  • Objective Metrics: The model achieved a Mel-cepstrum distortion (MCD) of ~3.0 dB, outperforming other non-parallel methods.
  • Data Efficiency: The model proved robust even when fine-tuning data was limited. Using only 100 non-parallel utterances, it still outperformed the VCC2018 baseline that used 500 utterances.

Limitations and Future Work

  • Prosody and Style: While the model handles duration well, the speaker embeddings are currently fixed vectors. The authors note that these embeddings don't yet fully capture complex "speaking styles" or emotional nuances.
  • One-Shot Conversion: The current model requires fine-tuning for each new speaker pair. The authors suggest that future work will investigate "one-shot" or "few-shot" conversion, where the model can mimic a new voice after hearing just a few seconds of audio without needing a dedicated training phase.
  • Vocoder Dependency: The quality is still partially dependent on the WaveNet vocoder used for final waveform synthesis, which is computationally expensive.

Summary updated

Abstract

This article presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion is achieved by preserving the linguistic representations of source utterances while replacing the speaker representations with the target ones. Our model is built under the framework of encoder-decoder neural networks. A recognition encoder is designed to learn the disentangled linguistic representations with two strategies. First, phoneme transcriptions of training data are introduced to provide the references for leaning linguistic representations of audio signals. Second, an adversarial training strategy is employed to further wipe out speaker information from the linguistic representations. Meanwhile, speaker representations are extracted from audio signals by a speaker encoder. The model parameters are estimated by two-stage training, including a pre-training stage using a multi-speaker dataset and a fine-tuning stage using the dataset of a specific conversion pair. Since both the recognition encoder and the decoder for recovering acoustic features are seq2seq neural networks, there are no constrains of frame alignment and frame-by-frame conversion in our proposed method. Experimental results showed that our method obtained higher similarity and naturalness than the best non-parallel voice conversion method in Voice Conversion Challenge 2018. Besides, the performance of our proposed method was closed to the state-of-the-art parallel seq2seq voice conversion method.
BibTeX
@article{zhang2020non,
  author = {Jing-Xuan Zhang and Zhen-Hua Ling and Li-Rong Dai},
  title = {{Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations}},
  journal = {IEEE ACM Trans. Audio Speech Lang. Process.},
  year = {2020},
  url = {https://openreview.net/forum?id=kV343dCYbp},
}

Loading related content...

Figure