While the Turkish language is listed among low-resource languages, literature on Turkish automatic speech recognition (ASR) is relatively old. In this paper, we present HuBERT-TR, a speech representation model for Turkish based on HuBERT. HuBERT-TR achieves state-of-the-art results on several Turkish ASR datasets. We investigate pre-training HuBERT for Turkish with large-scale data curated from online resources. We pre-train HuBERT-TR using over 6,500 hours of speech data curated from YouTube that includes extensive variability in terms of quality and genre. We show that pre-trained models within a multi-lingual setup are inferior to language-specific models, where our Turkish model HuBERT-TR base performs better than its x10 times larger multi-lingual counterpart XLS-R-1B. Moreover, we study the effect of scaling on ASR performance by scaling our models up to 1B parameters. Our best model yields a state-of-the-art word error rate of 4.97% on the Turkish Broadcast News dataset. Models are available at huggingface.co/asafaya .
Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose SpeechCLIP, a novel framework bridging speech and text through images to enhance speech models without transcriptions. We leverage state-of-the-art pre-trained HuBERT and CLIP, aligning them via paired images and spoken captions with minimal fine-tuning. SpeechCLIP outperforms prior state-of-the-art on image-speech retrieval and performs zero-shot speech-text retrieval without direct supervision from transcriptions. Moreover, SpeechCLIP can directly retrieve semantically related keywords from speech.
It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech recognition (ASR) models to extract textual embeddings as input to infer semantics, which, however, require computationally expensive auto-regressive decoding. In this work, we leverage self-supervised acoustic encoders fine-tuned with Connectionist Temporal Classification (CTC) to extract textual embeddings and use joint CTC and SLU losses for utterance-level SLU tasks. Experiments show that our model achieves 4% absolute improvement over the the state-of-the-art (SOTA) dialogue act classification model on the DSTC2 dataset and 1.3% absolute improvement over the SOTA SLU model on the SLURP dataset.
In a range of recent works, object-centric architectures have been shown to be suitable for unsupervised scene decomposition in the vision domain. Inspired by these methods we present AudioSlots, a slot-centric generative model for blind source separation in the audio domain. AudioSlots is built using permutation-equivariant encoder and decoder networks. The encoder network based on the Transformer architecture learns to map a mixed audio spectrogram to an unordered set of independent source embeddings. The spatial broadcast decoder network learns to generate the source spectrograms from the source embeddings. We train the model in an end-to-end manner using a permutation invariant loss function. Our results on Libri2Mix speech separation constitute a proof of concept that this approach shows promise. We discuss the results and limitations of our approach in detail, and further outline potential ways to overcome the limitations and directions for future work.
Recently there have been efforts to introduce new benchmark tasks for spoken language understanding (SLU), like semantic parsing. In this paper, we describe our proposed spoken semantic parsing system for the quality track (Track 1) in Spoken Language Understanding Grand Challenge which is part of ICASSP Signal Processing Grand Challenge 2023. We experiment with both end-to-end and pipeline systems for this task. Strong automatic speech recognition (ASR) models like Whisper and pretrained Language models (LM) like BART are utilized inside our SLU framework to boost performance. We also investigate the output level combination of various models to get an exact match accuracy of 80.8, which won the 1st place at the challenge.
A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for either the subsequent calculation of fluency-related features or directly modeling speech fluency with an end-to-end approach. This paper describes a novel ASR-free approach for automatic fluency assessment using self-supervised learning (SSL). Specifically, wav2vec2.0 is used to extract frame-level speech features, followed by K-means clustering to assign a pseudo label (cluster index) to each frame. A BLSTM-based model is trained to predict an utterance-level fluency score from frame-level SSL features and the corresponding cluster indexes. Neither speech transcription nor time stamp information is required in the proposed system. It is ASR-free and can potentially avoid the ASR errors effect in practice. Experimental results carried out on non-native English databases show that the proposed approach significantly improves the performance in the "open response" scenario as compared to previous methods and matches the recently reported performance in the "read aloud" scenario.
Unsupervised speech enhancement based on variational autoencoders has shown promising performance compared with the commonly used supervised methods. This approach involves the use of a pre-trained deep speech prior along with a parametric noise model, where the noise parameters are learned from the noisy speech signal with an expectationmaximization (EM)-based method. The E-step involves an intractable latent posterior distribution. Existing algorithms to solve this step are either based on computationally heavy Monte Carlo Markov Chain sampling methods and variational inference, or inefficient optimization-based methods. In this paper, we propose a new approach based on Langevin dynamics that generates multiple sequences of samples and comes with a total variation-based regularization to incorporate temporal correlations of latent vectors. Our experiments demonstrate that the developed framework makes an effective compromise between computational efficiency and enhancement quality, and outperforms existing methods.
Filler words like ``um" or ``uh" are common in spontaneous speech. It is desirable to automatically detect and remove them in recordings, as they affect the fluency, confidence, and professionalism of speech. Previous studies and our preliminary experiments reveal that the biggest challenge in filler word detection is that fillers can be easily confused with other hard categories like ``a" or ``I". In this paper, we propose a novel filler word detection method that effectively addresses this challenge by adding auxiliary categories dynamically and applying an additional inter-category focal loss. The auxiliary categories force the model to explicitly model the confusing words by mining hard categories. In addition, inter-category focal loss adaptively adjusts the penalty weight between ``filler" and ``non-filler" categories to deal with other confusing words left in the ``non-filler" category. Our system achieves the best results, with a huge improvement compared to other methods on the PodcastFillers dataset.
While deep learning based speech enhancement systems have made rapid progress in improving the quality of speech signals, they can still produce outputs that contain artifacts and can sound unnatural. We propose a novel approach to speech enhancement aimed at improving perceptual quality and naturalness of enhanced signals by optimizing for key characteristics of speech. We first identify key acoustic parameters that have been found to correlate well with voice quality (e.g. jitter, shimmer, and spectral flux) and then propose objective functions which are aimed at reducing the difference between clean speech and enhanced speech with respect to these features. The full set of acoustic features is the extended Geneva Acoustic Parameter Set (eGeMAPS), which includes 25 different attributes associated with perception of speech. Given the non-differentiable nature of these feature computation, we first build differentiable estimators of the eGeMAPS and then use them to fine-tune existing speech enhancement systems. Our approach is generic and can be applied to any existing deep learning based enhancement systems to further improve the enhanced speech signals. Experimental results conducted on the Deep Noise Suppression (DNS) Challenge dataset shows that our approach can improve the state-of-the-art deep learning based enhancement systems.
Our work advances an approach for predicting hate speech in social media, drawing out the critical need to consider the discussions that follow a post to successfully detect when hateful discourse may arise. Using graph transformer networks, coupled with modelling attention and BERT-level natural language processing, our approach can capture context and anticipate upcoming anti-social behaviour. In this paper, we offer a detailed qualitative analysis of this solution for hate speech detection in social networks, leading to insights into where the method has the most impressive outcomes in comparison with competitors and identifying scenarios where there are challenges to achieving ideal performance. Included is an exploration of the kinds of posts that permeate social media today, including the use of hateful images. This suggests avenues for extending our model to be more comprehensive. A key insight is that the focus on reasoning about the concept of context positions us well to be able to support multi-modal analysis of online posts. We conclude with a reflection on how the problem we are addressing relates especially well to the theme of dynamic change, a critical concern for all AI solutions for social impact. We also comment briefly on how mental health well-being can be advanced with our work, through curated content attuned to the extent of hate in posts.