Rohit Kumar

Srijith Radhakrishnan, Chao-Han Huck Yang, Sumeer Ahmad Khan et al.

We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate speech transcription contexts. This marks a step towards a fresh paradigm in generative error correction within the realm of n-best hypotheses. Unlike the existing ranking-based rescoring methods, our approach adeptly uses distinct initialization techniques and parameter-efficient algorithms to boost ASR performance derived from pre-trained speech and text models. Through evaluation across diverse ASR datasets, we evaluate the stability and reproducibility of our fusion technique, demonstrating its improved word error rate relative (WERR) performance in comparison to n-best hypotheses by relatively 37.66%. To encourage future research, we have made our code and pre-trained models open source at https://github.com/Srijith-rkr/Whispering-LLaMA.

Audrey Cui, Ali Jahanian, Agata Lapedriza et al. · mit

We introduce the task of local relighting, which changes a photograph of a scene by switching on and off the light sources that are visible within the image. This new task differs from the traditional image relighting problem, as it introduces the challenge of detecting light sources and inferring the pattern of light that emanates from them. We propose an approach for local relighting that trains a model without supervision of any novel image dataset by using synthetically generated image pairs from another model. Concretely, we collect paired training images from a stylespace-manipulated GAN; then we use these images to train a conditional image-to-image model. To benchmark local relighting, we introduce Lonoff, a collection of 306 precisely aligned images taken in indoor spaces with different combinations of lights switched on. We show that our method significantly outperforms baseline methods based on GAN inversion. Finally, we demonstrate extensions of our method that control different light sources separately. We invite the community to tackle this new task of local relighting.

Anurenjan Purushothaman, Debottam Dutta, Rohit Kumar et al. · deepmind

Speech applications in far-field real world settings often deal with signals that are corrupted by reverberation. The task of dereverberation constitutes an important step to improve the audible quality and to reduce the error rates in applications like automatic speech recognition (ASR). We propose a unified framework of speech dereverberation for improving the speech quality and the ASR performance using the approach of envelope-carrier decomposition provided by an autoregressive (AR) model. The AR model is applied in the frequency domain of the sub-band speech signals to separate the envelope and carrier parts. A novel neural architecture based on dual path long short term memory (DPLSTM) model is proposed, which jointly enhances the sub-band envelope and carrier components. The dereverberated envelope-carrier signals are modulated and the sub-band signals are synthesized to reconstruct the audio signal back. The DPLSTM model for dereverberation of envelope and carrier components also allows the joint learning of the network weights for the down stream ASR task. In the ASR tasks on the REVERB challenge dataset as well as on the VOiCES dataset, we illustrate that the joint learning of speech dereverberation network and the E2E ASR model yields significant performance improvements over the baseline ASR system trained on log-mel spectrogram as well as other benchmarks for dereverberation (average relative improvements of 10-24% over the baseline system). The speech quality improvements, evaluated using subjective listening tests, further highlight the improved quality of the reconstructed audio.

Pankaj Deoli, Rohit Kumar, Axel Vierling et al.

This study investigates the vulnerability of semantic segmentation models to adversarial input perturbations, in the domain of off-road autonomous driving. Despite good performance in generic conditions, the state-of-the-art classifiers are often susceptible to (even) small perturbations, ultimately resulting in inaccurate predictions with high confidence. Prior research has directed their focus on making models more robust by modifying the architecture and training with noisy input images, but has not explored the influence of datasets in adversarial attacks. Our study aims to address this gap by examining the impact of non-robust features in off-road datasets and comparing the effects of adversarial attacks on different segmentation network architectures. To enable this, a robust dataset is created consisting of only robust features and training the networks on this robustified dataset. We present both qualitative and quantitative analysis of our findings, which have important implications on improving the robustness of machine learning models in off-road autonomous driving applications. Additionally, this work contributes to the safe navigation of autonomous robot Unimog U5023 in rough off-road unstructured environments by evaluating the robustness of segmentation outputs. The code is publicly available at https://github.com/rohtkumar/adversarial_attacks_ on_segmentation

Anurenjan Purushothaman, Anirudh Sreeram, Rohit Kumar et al.

The task of speech recognition in far-field environments is adversely affected by the reverberant artifacts that elicit as the temporal smearing of the sub-band envelopes. In this paper, we develop a neural model for speech dereverberation using the long-term sub-band envelopes of speech. The sub-band envelopes are derived using frequency domain linear prediction (FDLP) which performs an autoregressive estimation of the Hilbert envelopes. The neural dereverberation model estimates the envelope gain which when applied to reverberant signals suppresses the late reflection components in the far-field signal. The dereverberated envelopes are used for feature extraction in speech recognition. Further, the sequence of steps involved in envelope dereverberation, feature extraction and acoustic modeling for ASR can be implemented as a single neural processing pipeline which allows the joint learning of the dereverberation network and the acoustic model. Several experiments are performed on the REVERB challenge dataset, CHiME-3 dataset and VOiCES dataset. In these experiments, the joint learning of envelope dereverberation and acoustic model yields significant performance improvements over the baseline ASR system based on log-mel spectrogram as well as other past approaches for dereverberation (average relative improvements of 10-24% over the baseline system). A detailed analysis on the choice of hyper-parameters and the cost function involved in envelope dereverberation is also provided.

R G Prithvi Raj, Rohit Kumar, M K Jayesh et al.

This paper presents the details of the SRIB-LEAP submission to the ConferencingSpeech challenge 2021. The challenge involved the task of multi-channel speech enhancement to improve the quality of far field speech from microphone arrays in a video conferencing room. We propose a two stage method involving a beamformer followed by single channel enhancement. For the beamformer, we incorporated self-attention mechanism as inter-channel processing layer in the filter-and-sum network (FaSNet), an end-to-end time-domain beamforming system. The single channel speech enhancement is done in log spectral domain using convolution neural network (CNN)-long short term memory (LSTM) based architecture. We achieved improvements in objective quality metrics - perceptual evaluation of speech quality (PESQ) of 0.5 on the noisy data. On subjective quality evaluation, the proposed approach improved the mean opinion score (MOS) by an absolute measure of 0.9 over the noisy audio.

Rohit Kumar, Anirudh Sreeram, Anurenjan Purushothaman et al.

The state-of-art methods for acoustic beamforming in multi-channel ASR are based on a neural mask estimator that predicts the presence of speech and noise. These models are trained using a paired corpus of clean and noisy recordings (teacher model). In this paper, we attempt to move away from the requirements of having supervised clean recordings for training the mask estimator. The models based on signal enhancement and beamforming using multi-channel linear prediction serve as the required mask estimate. In this way, the model training can also be carried out on real recordings of noisy speech rather than simulated ones alone done in a typical teacher model. Several experiments performed on noisy and reverberant environments in the CHiME-3 corpus as well as the REVERB challenge corpus highlight the effectiveness of the proposed approach. The ASR results for the proposed approach provide performances that are significantly better than a teacher model trained on an out-of-domain dataset and on par with the oracle mask estimators trained on the in-domain dataset.