Jae‐sung Bae

Jae-Sung Bae, Anastasia Kuznetsova, Dinesh Manocha et al.

This paper presents a new challenge that calls for zero-shot text-to-speech (TTS) systems to augment speech data for the downstream task, personalized speech enhancement (PSE), as part of the Generative Data Augmentation workshop at ICASSP 2025. Collecting high-quality personalized data is challenging due to privacy concerns and technical difficulties in recording audio from the test scene. To address these issues, synthetic data generation using generative models has gained significant attention. In this challenge, participants are tasked first with building zero-shot TTS systems to augment personalized data. Subsequently, PSE systems are asked to be trained with this augmented personalized dataset. Through this challenge, we aim to investigate how the quality of augmented data generated by zero-shot TTS models affects PSE model performance. We also provide baseline experiments using open-source zero-shot TTS models to encourage participation and benchmark advancements. Our baseline code implementation and checkpoints are available online.

Jinhyeok Yang, Jae-Sung Bae, Taejun Bak et al.

Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made it possible to synthesize the speech of a speaker with limited training data. Fine-tuning to the target speaker data with the multi-speaker model can achieve better quality, however, there still exists a gap compared to the real speech sample and the model depends on the speaker. In this work, we propose GANSpeech, which is a high-fidelity multi-speaker TTS model that adopts the adversarial training method to a non-autoregressive multi-speaker TTS model. In addition, we propose simple but efficient automatic scaling methods for feature matching loss used in adversarial training. In the subjective listening tests, GANSpeech significantly outperformed the baseline multi-speaker FastSpeech and FastSpeech2 models, and showed a better MOS score than the speaker-specific fine-tuned FastSpeech2.

Taejun Bak, Jae-Sung Bae, Hanbin Bae et al.

Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large pitch-shift scale suffers from audio quality degradation, and speaker characteristics deformation. To address this problem, we propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. This model, called FastPitchFormant, has a unique structure that handles text and acoustic features in parallel. With modeling each feature separately, the tendency that the model learns the relationship between two features can be mitigated.

Hanbin Bae, Jae-Sung Bae, Young-Sun Joo et al.

Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient and the remainder includes background music. Even with the global style token (GST). Therefore, we propose the following method to successfully train an end-to-end TTS model with limited broadcast data. First, the background music is removed from the speech by introducing a music filter. Second, the GST-TTS model with an auxiliary quality classifier is trained with the filtered speech and a small amount of clean speech. In particular, the quality classifier makes the embedding vector of the GST layer focus on representing the speech quality (filtered or clean) of the input speech. The experimental results verified that the proposed method synthesized much more high-quality speech than conventional methods.

Jae-Sung Bae, Hanbin Bae, Young-Sun Joo et al.

This paper proposes a controllable end-to-end text-to-speech (TTS) system to control the speaking speed (speed-controllable TTS; SCTTS) of synthesized speech with sentence-level speaking-rate value as an additional input. The speaking-rate value, the ratio of the number of input phonemes to the length of input speech, is adopted in the proposed system to control the speaking speed. Furthermore, the proposed SCTTS system can control the speaking speed while retaining other speech attributes, such as the pitch, by adopting the global style token-based style encoder. The proposed SCTTS does not require any additional well-trained model or an external speech database to extract phoneme-level duration information and can be trained in an end-to-end manner. In addition, our listening tests on fast-, normal-, and slow-speed speech showed that the SCTTS can generate more natural speech than other phoneme duration control approaches which increase or decrease duration at the same rate for the entire sentence, especially in the case of slow-speed speech.

Juntae Kim, Jaesung Bae, Minsoo Hahn

A state transition model (STM) based on chunk-wise classification was proposed for end-point detection (EPD). In general, EPD is developed using frame-wise voice activity detection (VAD) with additional STM, in which the state transition is conducted based on VAD's frame-level decision (speech or non-speech). However, VAD errors frequently occur in noisy environments, even though we use state-of-the-art deep neural network based VAD, which causes the undesired state transition of STM. In this work, to build robust STM, a state transition is conducted based on chunk-wise classification as EPD does not need to be conducted in frame-level. The chunk consists of multiple frames and the classification of chunk between speech and non-speech is done by aggregating the decisions of VAD for multiple frames, so that some undesired VAD errors in a chunk can be smoothed by other correct VAD decisions. Finally, the model was evaluated in both qualitative and quantitative measures including phone error rate.