Multimodal emotion recognition (MER) aims to detect the emotional status of a given expression by combining the speech and text information. Intuitively, label information should be capable of helping the model locate the salient tokens/frames relevant to the specific emotion, which finally facilitates the MER task. Inspired by this, we propose a novel approach for MER by leveraging label information. Specifically, we first obtain the representative label embeddings for both text and speech modalities, then learn the label-enhanced text/speech representations for each utterance via label-token and label-frame interactions. Finally, we devise a novel label-guided attentive fusion module to fuse the label-aware text and speech representations for emotion classification. Extensive experiments were conducted on the public IEMOCAP dataset, and experimental results demonstrate that our proposed approach outperforms existing baselines and achieves new state-of-the-art performance.
Temporal connectionist temporal classification (CTC)-based automatic speech recognition (ASR) is one of the most successful end to end (E2E) ASR frameworks. However, due to the token independence assumption in decoding, an external language model (LM) is required which destroys its fast parallel decoding property. Several studies have been proposed to transfer linguistic knowledge from a pretrained LM (PLM) to the CTC based ASR. Since the PLM is built from text while the acoustic model is trained with speech, a cross-modal alignment is required in order to transfer the context dependent linguistic knowledge from the PLM to acoustic encoding. In this study, we propose a novel cross-modal alignment algorithm based on optimal transport (OT). In the alignment process, a transport coupling matrix is obtained using OT, which is then utilized to transform a latent acoustic representation for matching the context-dependent linguistic features encoded by the PLM. Based on the alignment, the latent acoustic feature is forced to encode context dependent linguistic information. We integrate this latent acoustic feature to build conformer encoder-based CTC ASR system. On the AISHELL-1 data corpus, our system achieved 3.96% and 4.27% character error rate (CER) for dev and test sets, respectively, which corresponds to relative improvements of 28.39% and 29.42% compared to the baseline conformer CTC ASR system without cross-modal knowledge transfer.
This paper presents Translatotron 3, a novel approach to train a direct speech-to-speech translation model from monolingual speech-text datasets only in a fully unsupervised manner. Translatotron 3 combines masked autoencoder, unsupervised embedding mapping, and back-translation to achieve this goal. Experimental results in speech-to-speech translation tasks between Spanish and English show that Translatotron 3 outperforms a baseline cascade system, reporting 18.14 BLEU points improvement on the synthesized Unpaired-Conversational dataset. In contrast to supervised approaches that necessitate real paired data, which is unavailable, or specialized modeling to replicate para-/non-linguistic information, Translatotron 3 showcases its capability to retain para-/non-linguistic such as pauses, speaking rates, and speaker identity. Audio samples can be found in our website http://google-research.github.io/lingvo-lab/translatotron3
Voice disorders affect millions of people worldwide. Surface electromyography-based Silent Speech Interfaces (sEMG-based SSIs) have been explored as a potential solution for decades. However, previous works were limited by small vocabularies and manually extracted features from raw data. To address these limitations, we propose a lightweight deep learning knowledge-distilled ensemble model for sEMG-based SSI (KDE-SSI). Our model can classify a 26 NATO phonetic alphabets dataset with 3900 data samples, enabling the unambiguous generation of any English word through spelling. Extensive experiments validate the effectiveness of KDE-SSI, achieving a test accuracy of 85.9\%. Our findings also shed light on an end-to-end system for portable, practical equipment.
Vector Quantization (VQ) is a well-known technique in deep learning for extracting informative discrete latent representations. VQ-embedded models have shown impressive results in a range of applications including image and speech generation. VQ operates as a parametric K-means algorithm that quantizes inputs using a single codebook vector in the forward pass. While powerful, this technique faces practical challenges including codebook collapse, non-differentiability and lossy compression. To mitigate the aforementioned issues, we propose Soft Convex Quantization (SCQ) as a direct substitute for VQ. SCQ works like a differentiable convex optimization (DCO) layer: in the forward pass, we solve for the optimal convex combination of codebook vectors that quantize the inputs. In the backward pass, we leverage differentiability through the optimality conditions of the forward solution. We then introduce a scalable relaxation of the SCQ optimization and demonstrate its efficacy on the CIFAR-10, GTSRB and LSUN datasets. We train powerful SCQ autoencoder models that significantly outperform matched VQ-based architectures, observing an order of magnitude better image reconstruction and codebook usage with comparable quantization runtime.
Discriminatory language and biases are often present in hate speech during conversations, which usually lead to negative impacts on targeted groups such as those based on race, gender, and religion. To tackle this issue, we propose an approach that involves a two-step process: first, detecting hate speech using a classifier, and then utilizing a debiasing component that generates less biased or unbiased alternatives through prompts. We evaluated our approach on a benchmark dataset and observed reduction in negativity due to hate speech comments. The proposed method contributes to the ongoing efforts to reduce biases in online discourse and promote a more inclusive and fair environment for communication.
Previous methods for predicting room acoustic parameters and speech quality metrics have focused on the single-channel case, where room acoustics and Mean Opinion Score (MOS) are predicted for a single recording device. However, quality-based device selection for rooms with multiple recording devices may benefit from a multi-channel approach where the descriptive metrics are predicted for multiple devices in parallel. Following our hypothesis that a model may benefit from multi-channel training, we develop a multi-channel model for joint MOS and room acoustics prediction (MOSRA) for five channels in parallel. The lack of multi-channel audio data with ground truth labels necessitated the creation of simulated data using an acoustic simulator with room acoustic labels extracted from the generated impulse responses and labels for MOS generated in a student-teacher setup using a wav2vec2-based MOS prediction model. Our experiments show that the multi-channel model improves the prediction of the direct-to-reverberation ratio, clarity, and speech transmission index over the single-channel model with roughly 5$\times$ less computation while suffering minimal losses in the performance of the other metrics.
Convolutional neural networks (CNN) and Transformer have wildly succeeded in multimedia applications. However, more effort needs to be made to harmonize these two architectures effectively to satisfy speech enhancement. This paper aims to unify these two architectures and presents a Parallel Conformer for speech enhancement. In particular, the CNN and the self-attention (SA) in the Transformer are fully exploited for local format patterns and global structure representations. Based on the small receptive field size of CNN and the high computational complexity of SA, we specially designed a multi-branch dilated convolution (MBDC) and a self-channel-time-frequency attention (Self-CTFA) module. MBDC contains three convolutional layers with different dilation rates for the feature from local to non-local processing. Experimental results show that our method performs better than state-of-the-art methods in most evaluation criteria while maintaining the lowest model parameters.
We propose a method for speech-to-speech emotionpreserving translation that operates at the level of discrete speech units. Our approach relies on the use of multilingual emotion embedding that can capture affective information in a language-independent manner. We show that this embedding can be used to predict the pitch and duration of speech units in a target language, allowing us to resynthesize the source speech signal with the same emotional content. We evaluate our approach to English and French speech signals and show that it outperforms a baseline method that does not use emotional information, including when the emotion embedding is extracted from a different language. Even if this preliminary study does not address directly the machine translation issue, our results demonstrate the effectiveness of our approach for cross-lingual emotion preservation in the context of speech resynthesis.
Attention-based encoder-decoder models with autoregressive (AR) decoding have proven to be the dominant approach for automatic speech recognition (ASR) due to their superior accuracy. However, they often suffer from slow inference. This is primarily attributed to the incremental calculation of the decoder. This work proposes a partially AR framework, which employs segment-level vectorized beam search for improving the inference speed of an ASR model based on the hybrid connectionist temporal classification (CTC) attention-based architecture. It first generates an initial hypothesis using greedy CTC decoding, identifying low-confidence tokens based on their output probabilities. We then utilize the decoder to perform segment-level vectorized beam search on these tokens, re-predicting in parallel with minimal decoder calculations. Experimental results show that our method is 12 to 13 times faster in inference on the LibriSpeech corpus over AR decoding whilst preserving high accuracy.