Identifying keywords in an open-vocabulary context is crucial for personalizing interactions with smart devices. Previous approaches to open vocabulary keyword spotting dependon a shared embedding space created by audio and text encoders. However, these approaches suffer from heterogeneous modality representations (i.e., audio-text mismatch). To address this issue, our proposed framework leverages knowledge acquired from a pre-trained text-to-speech (TTS) system. This knowledge transfer allows for the incorporation of awareness of audio projections into the text representations derived from the text encoder. The performance of the proposed approach is compared with various baseline methods across four different datasets. The robustness of our proposed model is evaluated by assessing its performance across different word lengths and in an Out-of-Vocabulary (OOV) scenario. Additionally, the effectiveness of transfer learning from the TTS system is investigated by analyzing its different intermediate representations. The experimental results indicate that, in the challenging LibriPhrase Hard dataset, the proposed approach outperformed the cross-modality correspondence detector (CMCD) method by a significant improvement of 8.22% in area under the curve (AUC) and 12.56% in equal error rate (EER).
There have been emerging research interest and advances in speech-to-speech translation (S2ST), translating utterances from one language to another. This work proposes Multitask Speech Language Model (MSLM), which is a decoder-only speech language model trained in a multitask setting. Without reliance on text training data, our model is able to support multilingual S2ST with speaker style preserved.
We present UTDUSS, the UTokyo-SaruLab system submitted to Interspeech2024 Speech Processing Using Discrete Speech Unit Challenge. The challenge focuses on using discrete speech unit learned from large speech corpora for some tasks. We submitted our UTDUSS system to two text-to-speech tracks: Vocoder and Acoustic+Vocoder. Our system incorporates neural audio codec (NAC) pre-trained on only speech corpora, which makes the learned codec represent rich acoustic features that are necessary for high-fidelity speech reconstruction. For the acoustic+vocoder track, we trained an acoustic model based on Transformer encoder-decoder that predicted the pre-trained NAC tokens from text input. We describe our strategies to build these models, such as data selection, downsampling, and hyper-parameter tuning. Our system ranked in second and first for the Vocoder and Acoustic+Vocoder tracks, respectively.
This paper presents a novel neural speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra. The proposed model is a cascade of a residual convolutional network and a parallel estimation architecture. The parallel estimation architecture is a core module for direct wrapped phase prediction. This architecture consists of two parallel linear convolutional layers and a phase calculation formula, imitating the process of calculating the phase spectra from the real and imaginary parts of complex spectra and strictly restricting the predicted phase values to the principal value interval. To avoid the error expansion issue caused by phase wrapping, we design anti-wrapping training losses defined between the predicted wrapped phase spectra and natural ones by activating the instantaneous phase error, group delay error and instantaneous angular frequency error using an anti-wrapping function. We mathematically demonstrate that the anti-wrapping function should possess three properties, namely parity, periodicity and monotonicity. We also achieve low-latency streamable phase prediction by combining causal convolutions and knowledge distillation training strategies. For both analysis-synthesis and specific speech generation tasks, experimental results show that our proposed neural speech phase prediction model outperforms the iterative phase estimation algorithms and neural network-based phase prediction methods in terms of phase prediction precision, efficiency and robustness. Compared with HiFi-GAN-based waveform reconstruction method, our proposed model also shows outstanding efficiency advantages while ensuring the quality of synthesized speech. To the best of our knowledge, we are the first to directly predict speech phase spectra from amplitude spectra only via neural networks.
Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification, largely due to data scarcity. To deal with this challenge, current works tend to segment patients' audio files into many samples to augment the datasets. Nevertheless, this approach has limitations, as it indirectly relates overall audio scores to individual segments. This paper introduces a novel approach where the system learns at the audio level instead of segments despite data scarcity. This paper proposes to use the pre-trained Wav2Vec2 architecture for both SSL, and ASR as feature extractor in speech assessment. Carried out on the HNC dataset, our ASR-driven approach established a new baseline compared with other approaches, obtaining average $MSE=0.73$ and $MSE=1.15$ for the prediction of intelligibility and severity scores respectively, using only 95 training samples. It shows that the ASR based Wav2Vec2 model brings the best results and may indicate a strong correlation between ASR and speech quality assessment. We also measure its ability on variable segment durations and speech content, exploring factors influencing its decision.
The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one consists of coded or indirect language. Therefore, it is crucial for models not only to detect implicit toxic speech but also to explain its toxicity. This draws a unique need for unified frameworks that can effectively detect and explain implicit toxic speech. Prior works mainly formulated the task of toxic speech detection and explanation as a text generation problem. Nonetheless, models trained using this strategy can be prone to suffer from the consequent error propagation problem. Moreover, our experiments reveal that the detection results of such models are much lower than those that focus only on the detection task. To bridge these gaps, we introduce ToXCL, a unified framework for the detection and explanation of implicit toxic speech. Our model consists of three modules: a (i) Target Group Generator to generate the targeted demographic group(s) of a given post; an (ii) Encoder-Decoder Model in which the encoder focuses on detecting implicit toxic speech and is boosted by a (iii) Teacher Classifier via knowledge distillation, and the decoder generates the necessary explanation. ToXCL achieves new state-of-the-art effectiveness, and outperforms baselines significantly.
Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar performance compared to traditional methods. However, SSL-based ASA systems are faced with at least three data-related challenges: limited annotated data, uneven distribution of learner proficiency levels and non-uniform score intervals between different CEFR proficiency levels. To address these challenges, we explore the use of two novel modeling strategies: metric-based classification and loss reweighting, leveraging distinct SSL-based embedding features. Extensive experimental results on the ICNALE benchmark dataset suggest that our approach can outperform existing strong baselines by a sizable margin, achieving a significant improvement of more than 10% in CEFR prediction accuracy.
This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we perform Noisy Student Training after generating pseudo-labels for the unlabeled public data using a strong Conformer RNN-T baseline model. The addition of these pseudo-labeled data results in remarkable improvements in relative Word Error Rate (WER) by 11.5% and 24.3% for our asynchronous and realtime models, respectively. Additionally, the model is more robust to background noise owing to the addition of these data. The results obtained in this study demonstrate that the incorporation of pseudo-labeled publicly available data is a highly effective strategy for improving ASR accuracy and noise robustness.
In this paper we address the challenge of improving Automatic Speech Recognition (ASR) for a low-resource language, Hawaiian, by incorporating large amounts of independent text data into an ASR foundation model, Whisper. To do this, we train an external language model (LM) on ~1.5M words of Hawaiian text. We then use the LM to rescore Whisper and compute word error rates (WERs) on a manually curated test set of labeled Hawaiian data. As a baseline, we use Whisper without an external LM. Experimental results reveal a small but significant improvement in WER when ASR outputs are rescored with a Hawaiian LM. The results support leveraging all available data in the development of ASR systems for underrepresented languages.
There is increasing interest in the use of the LEArnable Front-end (LEAF) in a variety of speech processing systems. However, there is a dearth of analyses of what is actually learnt and the relative importance of training the different components of the front-end. In this paper, we investigate this question on keyword spotting, speech-based emotion recognition and language identification tasks and find that the filters for spectral decomposition and the low pass filter used to estimate spectral energy variations exhibit no learning and the per-channel energy normalisation (PCEN) is the key component that is learnt. Following this, we explore the potential of adapting only the PCEN layer with a small amount of noisy data to enable it to learn appropriate dynamic range compression that better suits the noise conditions. This in turn enables a system trained on clean speech to work more accurately on noisy test data as demonstrated by the experimental results reported in this paper.