End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare name entities, such as personal names, organizations, or technical terms that are not frequently encountered in the training data. This paper presents Contextual Biasing Whisper (CB-Whisper), a novel ASR system based on OpenAI's Whisper model that performs keyword-spotting (KWS) before the decoder. The KWS module leverages text-to-speech (TTS) techniques and a convolutional neural network (CNN) classifier to match the features between the entities and the utterances. Experiments demonstrate that by incorporating predicted entities into a carefully designed spoken form prompt, the mixed-error-rate (MER) and entity recall of the Whisper model is significantly improved on three internal datasets and two open-sourced datasets that cover English-only, Chinese-only, and code-switching scenarios.
Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is particularly desirable but presents a difficult technical challenge. In this work, we propose a method for predicting punctuated text from input speech using a chunk-based Transformer encoder trained with Connectionist Temporal Classification (CTC) loss. The acoustic model trained with long sequences by concatenating the input and target sequences can learn punctuation marks attached to the end of sentences more effectively. Additionally, by combining CTC losses on the chunks and utterances, we achieved both the improved F1 score of punctuation prediction and Word Error Rate (WER).
Multi-lingual speech recognition aims to distinguish linguistic expressions in different languages and integrate acoustic processing simultaneously. In contrast, current multi-lingual speech recognition research follows a language-aware paradigm, mainly targeted to improve recognition performance rather than discriminate language characteristics. In this paper, we present a multi-lingual speech recognition network named Mixture-of-Language-Expert(MoLE), which digests speech in a variety of languages. Specifically, MoLE analyzes linguistic expression from input speech in arbitrary languages, activating a language-specific expert with a lightweight language tokenizer. The tokenizer not only activates experts, but also estimates the reliability of the activation. Based on the reliability, the activated expert and the language-agnostic expert are aggregated to represent language-conditioned embedding for efficient speech recognition. Our proposed model is evaluated in 5 languages scenario, and the experimental results show that our structure is advantageous on multi-lingual recognition, especially for speech in low-resource language.
Wav2vec2 has achieved success in applying Transformer architecture and self-supervised learning to speech recognition. Recently, these have come to be used not only for speech recognition but also for the entire speech processing. This paper introduces an effective end-to-end speaker identification model applied Transformer-based contextual model. We explored the relationship between the parameters and the performance in order to discern the structure of an effective model. Furthermore, we propose a pooling method, Temporal Gate Pooling, with powerful learning ability for speaker identification. We applied Conformer as encoder and BEST-RQ for pre-training and conducted an evaluation utilizing the speaker identification of VoxCeleb1. The proposed method has achieved an accuracy of 85.9% with 28.5M parameters, demonstrating comparable precision to wav2vec2 with 317.7M parameters. Code is available at https://github.com/HarunoriKawano/speaker-identification-with-tgp.
Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition. In this work, we show that sequence discriminative training has a strong correlation with ILM subtraction from both theoretical and empirical points of view. Theoretically, we derive that the global optimum of maximum mutual information (MMI) training shares a similar formula as ILM subtraction. Empirically, we show that ILM subtraction and sequence discriminative training achieve similar performance across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context. The benefit of ILM subtraction also becomes much smaller after sequence discriminative training. We also provide an in-depth study to show that sequence discriminative training has a minimal effect on the commonly used zero-encoder ILM estimation, but a joint effect on both encoder and prediction + joint network for posterior probability reshaping including both ILM and blank suppression.
In this paper, we start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) and examining the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error rate between models trained using FL versus their centralized counterpart. Specifically, we study the effect of (i) adaptive optimizers, (ii) loss characteristics via altering Connectionist Temporal Classification (CTC) weight, (iii) model initialization through seed start, (iv) carrying over modeling setup from experiences in centralized training to FL, e.g., pre-layer or post-layer normalization, and (v) FL-specific hyperparameters, such as number of local epochs, client sampling size, and learning rate scheduler, specifically for ASR under heterogeneous data distribution. We shed light on how some optimizers work better than others via inducing smoothness. We also summarize the applicability of algorithms, trends, and propose best practices from prior works in FL (in general) toward End-to-End ASR models.
Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized fixed-point arithmetic to improve runtime memory and latency. In this work, we replicate the NNA operators during the training phase, accounting for the degradation due to low-precision inference on the NNA in back-propagation. Our proposed method efficiently emulates NNA operations, thus foregoing the need to transfer quantization error-prone data to the Central Processing Unit (CPU), ultimately reducing the user perceived latency (UPL). We apply our approach to Recurrent Neural Network-Transducer (RNN-T), an attractive architecture for on-device streaming speech recognition tasks. We train and evaluate models on 270K hours of English data and show a 5-7% improvement in engine latency while saving up to 10% relative degradation in WER.
Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA) models operate in the time domain. However, their overly simplistic approach to modeling acoustic features often necessitates larger and more computationally intensive models in order to achieve SOTA performance. In this paper, we present a novel time-frequency domain audio-visual speech separation method: Recurrent Time-Frequency Separation Network (RTFS-Net), which applies its algorithms on the complex time-frequency bins yielded by the Short-Time Fourier Transform. We model and capture the time and frequency dimensions of the audio independently using a multi-layered RNN along each dimension. Furthermore, we introduce a unique attention-based fusion technique for the efficient integration of audio and visual information, and a new mask separation approach that takes advantage of the intrinsic spectral nature of the acoustic features for a clearer separation. RTFS-Net outperforms the previous SOTA method using only 10% of the parameters and 18% of the MACs. This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.
Initialization of neural network weights plays a pivotal role in determining their performance. Feature Imitating Networks (FINs) offer a novel strategy by initializing weights to approximate specific closed-form statistical features, setting a promising foundation for deep learning architectures. While the applicability of FINs has been chiefly tested in biomedical domains, this study extends its exploration into other time series datasets. Three different experiments are conducted in this study to test the applicability of imitating Tsallis entropy for performance enhancement: Bitcoin price prediction, speech emotion recognition, and chronic neck pain detection. For the Bitcoin price prediction, models embedded with FINs reduced the root mean square error by around 1000 compared to the baseline. In the speech emotion recognition task, the FIN-augmented model increased classification accuracy by over 3 percent. Lastly, in the CNP detection experiment, an improvement of about 7 percent was observed compared to established classifiers. These findings validate the broad utility and potency of FINs in diverse applications.
Connectionist temporal classification (CTC) is commonly adopted for sequence modeling tasks like speech recognition, where it is necessary to preserve order between the input and target sequences. However, CTC is only applied to deterministic sequence models, where the latent space is discontinuous and sparse, which in turn makes them less capable of handling data variability when compared to variational models. In this paper, we integrate CTC with a variational model and derive loss functions that can be used to train more generalizable sequence models that preserve order. Specifically, we derive two versions of the novel variational CTC based on two reasonable assumptions, the first being that the variational latent variables at each time step are conditionally independent; and the second being that these latent variables are Markovian. We show that both loss functions allow direct optimization of the variational lower bound for the model log-likelihood, and present computationally tractable forms for implementing them.