# Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

arXiv: https://arxiv.org/abs/2203.12813 · HTML: https://mlsanity.com/paper/2203.12813/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines](https://mlsanity.com/paper/2010.11567/) (2020)
- [Unsupervised Speech Decomposition via Triple Information Bottleneck](https://mlsanity.com/paper/2004.11284/) (2020)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling](https://mlsanity.com/paper/2009.02725/) (2020)
- [Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks](https://mlsanity.com/paper/1704.00849/) (2017)
- [Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations](https://mlsanity.com/paper/1906.10508/) (2019)
- [CopyCat: Many-to-Many Fine-Grained Prosody Transfer for Neural Text-to-Speech](https://mlsanity.com/paper/2004.14617/) (2020)
- [Sequence-to-Sequence Acoustic Modeling for Voice Conversion](https://mlsanity.com/paper/1810.06865/) (2018)
- [Accent and Speaker Disentanglement in Many-to-many Voice Conversion](https://mlsanity.com/paper/2011.08609/) (2020)
- [Adversarially learning disentangled speech representations for robust multi-factor voice conversion](https://mlsanity.com/paper/2102.00184/) (2021)

## Built on by (most cited first, 10 of 10)

- [Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models](https://mlsanity.com/paper/2409.12139/) (2024)
- [Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning](https://mlsanity.com/paper/2505.15402/) (2025)
- [DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding](https://mlsanity.com/paper/2305.12425/) (2023)
- [Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching](https://mlsanity.com/paper/2411.02026/) (2024)
- [CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance](https://mlsanity.com/paper/2509.19883/) (2025)
- [Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencoder](https://mlsanity.com/paper/2211.08191/) (2022)
- [Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion](https://mlsanity.com/paper/2305.09167/) (2023)
- [Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling](https://mlsanity.com/paper/2410.01350/) (2024)
- [Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features](https://mlsanity.com/paper/2502.04722/) (2025)
- [Vibrato Expression Control for Singing Voice Conversion with Improving Independent Control](https://mlsanity.com/paper/2606.17126/) (2026)

## Abstract (arXiv)

Non-parallel data voice conversion (VC) have achieved considerable breakthroughs recently through introducing bottleneck features (BNFs) extracted by the automatic speech recognition(ASR) model. However, selection of BNFs have a significant impact on VC result. For example, when extracting BNFs from ASR trained with Cross Entropy loss (CE-BNFs) and feeding into neural network to train a VC system, the timbre similarity of converted speech is significantly degraded. If BNFs are extracted from ASR trained using Connectionist Temporal Classification loss (CTC-BNFs), the naturalness of the converted speech may decrease. This phenomenon is caused by the difference of information contained in BNFs. In this paper, we proposed an any-to-one VC method using hybrid bottleneck features extracted from CTC-BNFs and CE-BNFs to complement each other advantages. Gradient reversal layer and instance normalization were used to extract prosody information from CE-BNFs and content information from CTC-BNFs. Auto-regressive decoder and Hifi-GAN vocoder were used to generate high-quality waveform. Experimental results show that our proposed method achieves higher similarity, naturalness, quality than baseline method and reveals the differences between the information contained in CE-BNFs and CTC-BNFs as well as the influence they have on the converted speech.