This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that learns from BERT's token probabilities. Our method shows that language model (LM) information can be more effectively distilled into an ASR model using both the intermediate layers and the final layer. By using the intermediate layers as distillation target, we can more effectively distil LM knowledge into the lower network layers. Using our method, we achieve better recognition accuracy than with shallow fusion of an external LM, allowing us to maintain fast parallel decoding. Experiments on the LibriSpeech dataset demonstrate the effectiveness of our approach in enhancing greedy decoding with connectionist temporal classification (CTC).
We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis system that allows control over speaker identity using natural language descriptions. To control speaker identity within the prompt-based TTS framework, we introduce the concept of speaker prompt, which describes voice characteristics (e.g., gender-neutral, young, old, and muffled) designed to be approximately independent of speaking style. Since there is no large-scale dataset containing speaker prompts, we first construct a dataset based on the LibriTTS-R corpus with manually annotated speaker prompts. We then employ a diffusion-based acoustic model with mixture density networks to model diverse speaker factors in the training data. Unlike previous studies that rely on style prompts describing only a limited aspect of speaker individuality, such as pitch, speaking speed, and energy, our method utilizes an additional speaker prompt to effectively learn the mapping from natural language descriptions to the acoustic features of diverse speakers. Our subjective evaluation results show that the proposed method can better control speaker characteristics than the methods without the speaker prompt. Audio samples are available at https://reppy4620.github.io/demo.promptttspp/.
This study introduces a novel training paradigm, audio difference learning, for improving audio captioning. The fundamental concept of the proposed learning method is to create a feature representation space that preserves the relationship between audio, enabling the generation of captions that detail intricate audio information. This method employs a reference audio along with the input audio, both of which are transformed into feature representations via a shared encoder. Captions are then generated from these differential features to describe their differences. Furthermore, a unique technique is proposed that involves mixing the input audio with additional audio, and using the additional audio as a reference. This results in the difference between the mixed audio and the reference audio reverting back to the original input audio. This allows the original input's caption to be used as the caption for their difference, eliminating the need for additional annotations for the differences. In the experiments using the Clotho and ESC50 datasets, the proposed method demonstrated an improvement in the SPIDEr score by 7% compared to conventional methods.
End-to-end neural diarization (EEND) with encoder-decoder-based attractors (EDA) is a promising method to handle the whole speaker diarization problem simultaneously with a single neural network. While the EEND model can produce all frame-level speaker labels simultaneously, it disregards output label dependency. In this work, we propose a novel EEND model that introduces the label dependency between frames. The proposed method generates non-autoregressive intermediate attractors to produce speaker labels at the lower layers and conditions the subsequent layers with these labels. While the proposed model works in a non-autoregressive manner, the speaker labels are refined by referring to the whole sequence of intermediate labels. The experiments with the two-speaker CALLHOME dataset show that the intermediate labels with the proposed non-autoregressive intermediate attractors boost the diarization performance. The proposed method with the deeper network benefits more from the intermediate labels, resulting in better performance and training throughput than EEND-EDA.
Acoustic scene classification (ASC) and sound event detection (SED) are fundamental tasks in environmental sound analysis, and many methods based on deep learning have been proposed. Considering that information on acoustic scenes and sound events helps SED and ASC mutually, some researchers have proposed a joint analysis of acoustic scenes and sound events by multitask learning (MTL). However, conventional works have not investigated in detail how acoustic scenes and sound events mutually benefit SED and ASC. We, therefore, investigate the impact of information on acoustic scenes and sound events on the performance of SED and ASC by using domain adversarial training based on a gradient reversal layer (GRL) or model training with fake labels. Experimental results obtained using the TUT Acoustic Scenes 2016/2017 and TUT Sound Events 2016/2017 show that pieces of information on acoustic scenes and sound events are effectively used to detect sound events and classify acoustic scenes, respectively. Moreover, upon comparing GRL- and fake-label-based methods with single-task-based ASC and SED methods, single-task-based methods are found to achieve better performance. This result implies that even when using single-task-based ASC and SED methods, information on acoustic scenes may be implicitly utilized for SED and vice versa.
This paper proposes a method for improved CTC inference with searched intermediates and multi-pass conditioning. The paper first formulates self-conditioned CTC as a probabilistic model with an intermediate prediction as a latent representation and provides a tractable conditioning framework. We then propose two new conditioning methods based on the new formulation: (1) Searched intermediate conditioning that refines intermediate predictions with beam-search, (2) Multi-pass conditioning that uses predictions of previous inference for conditioning the next inference. These new approaches enable better conditioning than the original self-conditioned CTC during inference and improve the final performance. Experiments with the LibriSpeech dataset show relative 3%/12% performance improvement at the maximum in test clean/other sets compared to the original self-conditioned CTC.
End-to-end automatic speech recognition (ASR) directly maps input speech to a character sequence without using pronunciation lexica. However, in languages with thousands of characters, such as Japanese and Mandarin, modeling all these characters is problematic due to data scarcity. To alleviate the problem, we propose a multi-task learning model with explicit interaction between characters and syllables by utilizing Self-conditioned connectionist temporal classification (CTC) technique. While the original Self-conditioned CTC estimates character-level intermediate predictions by applying auxiliary CTC losses to a set of intermediate layers, the proposed method additionally estimates syllable-level intermediate predictions in another set of intermediate layers. The character-level and syllable-level predictions are alternately used as conditioning features to deal with mutual dependency between characters and syllables. Experimental results on Japanese and Mandarin datasets show that the proposed multi-sequence intermediate conditioning outperformed the conventional multi-task-based and Self-conditioned CTC-based methods.
This paper proposes InterAug: a novel training method for CTC-based ASR using augmented intermediate representations for conditioning. The proposed method exploits the conditioning framework of self-conditioned CTC to train robust models by conditioning with "noisy" intermediate predictions. During the training, intermediate predictions are changed to incorrect intermediate predictions, and fed into the next layer for conditioning. The subsequent layers are trained to correct the incorrect intermediate predictions with the intermediate losses. By repeating the augmentation and the correction, iterative refinements, which generally require a special decoder, can be realized only with the audio encoder. To produce noisy intermediate predictions, we also introduce new augmentation: intermediate feature space augmentation and intermediate token space augmentation that are designed to simulate typical errors. The combination of the proposed InterAug framework with new augmentation allows explicit training of the robust audio encoders. In experiments using augmentations simulating deletion, insertion, and substitution error, we confirmed that the trained model acquires robustness to each error, boosting the speech recognition performance of the strong self-conditioned CTC baseline.
This paper proposes CTC-based non-autoregressive ASR with self-conditioned folded encoders. The proposed method realizes non-autoregressive ASR with fewer parameters by folding the conventional stack of encoders into only two blocks; base encoders and folded encoders. The base encoders convert the input audio features into a neural representation suitable for recognition. This is followed by the folded encoders applied repeatedly for further refinement. Applying the CTC loss to the outputs of all encoders enforces the consistency of the input-output relationship. Thus, folded encoders learn to perform the same operations as an encoder with deeper distinct layers. In experiments, we investigate how to set the number of layers and the number of iterations for the base and folded encoders. The results show that the proposed method achieves a performance comparable to that of the conventional method using only 38% as many parameters. Furthermore, it outperforms the conventional method when increasing the number of iterations.
This paper proposes acoustic event detection (AED) with classifier chains, a new classifier based on the probabilistic chain rule. The proposed AED with classifier chains consists of a gated recurrent unit and performs iterative binary detection of each event one by one. In each iteration, the event's activity is estimated and used to condition the next output based on the probabilistic chain rule to form classifier chains. Therefore, the proposed method can handle the interdependence among events upon classification, while the conventional AED methods with multiple binary classifiers with a linear layer and sigmoid function have placed an assumption of conditional independence. In the experiments with a real-recording dataset, the proposed method demonstrates its superior AED performance to a relative 14.80% improvement compared to a convolutional recurrent neural network baseline system with the multiple binary classifiers.