arXiv subjects

Sanjeev Khudanpur

Publications and source records attributed to Sanjeev Khudanpur.

At least 73 records · Page 4Linked to original sources

arXiv2021

Lhotse: a speech data representation library for the modern deep learning ecosystem

Speech data is notoriously difficult to work with due to a variety of codecs, lengths of recordings, and meta-data formats. We present Lhotse, a speech data representation library that draws upon lessons learned from Kaldi speech recognition toolkit and brings its concepts into the modern deep learning ecosystem. Lhotse provides a common JSON description format with corresponding Python classes and data preparation recipes for over 30 popular speech corpora. Various datasets can be easily combined together and re-purposed for different tasks. The library handles multi-channel recordings, long recordings, local and cloud storage, lazy and on-the-fly operations amongst other features. We introduce Cut and CutSet concepts, which simplify common data wrangling tasks for audio and help incorporate acoustic context of speech utterances. Finally, we show how Lhotse leverages PyTorch data API abstractions and adopts them to handle speech data for deep learning.

cs.SD↗

arXiv2021

Injecting Text and Cross-lingual Supervision in Few-shot Learning from Self-Supervised Models

Self-supervised model pre-training has recently garnered significant interest, but relatively few efforts have explored using additional resources in fine-tuning these models. We demonstrate how universal phoneset acoustic models can leverage cross-lingual supervision to improve transfer of pretrained self-supervised representations to new languages. We also show how target-language text can be used to enable and improve fine-tuning with the lattice-free maximum mutual information (LF-MMI) objective. In three low-resource languages these techniques greatly improved few-shot learning performance.

eess.AS↗

arXiv2021

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.

cs.SD↗

arXiv2021

Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

We recently proposed DOVER-Lap, a method for combining overlap-aware speaker diarization system outputs. DOVER-Lap improved upon its predecessor DOVER by using a label mapping method based on globally-informed greedy search. In this paper, we analyze this label mapping in the framework of a maximum orthogonal graph partitioning problem, and present three inferences. First, we show that DOVER-Lap label mapping is exponential in the input size, which poses a challenge when combining a large number of hypotheses. We then revisit the DOVER label mapping algorithm and propose a modification which performs similar to DOVER-Lap while being computationally tractable. We also derive an approximation bound for the algorithm in terms of the maximum number of hypotheses speakers. Finally, we describe a randomized local search algorithm which provides a near-optimal $(1-ε)$-approximate solution to the problem with high probability. We empirically demonstrate the effectiveness of our methods on the AMI meeting corpus. Our code is publicly available: https://github.com/desh2608/dover-lap.

eess.AS↗

arXiv2021

Adversarial Attacks and Defenses for Speech Recognition Systems

The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks and defenses against automatic speech recognition (ASR) systems. We select two ASR models - a thoroughly studied DeepSpeech model and a more recent Espresso framework Transformer encoder-decoder model. We investigate two threat models: a denial-of-service scenario where fast gradient-sign method (FGSM) or weak projected gradient descent (PGD) attacks are used to degrade the model's word error rate (WER); and a targeted scenario where a more potent imperceptible attack forces the system to recognize a specific phrase. We find that the attack transferability across the investigated ASR systems is limited. To defend the model, we use two preprocessing defenses: randomized smoothing and WaveGAN-based vocoder, and find that they significantly improve the model's adversarial robustness. We show that a WaveGAN vocoder can be a useful countermeasure to adversarial attacks on ASR systems - even when it is jointly attacked with the ASR, the target phrases' word error rate is high.

eess.AS↗

arXiv2021

An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which might induce a significant computation overhead, the asynchronous dynamic decoder has a novel design where it has two fronts, with one performing "exploration" and the other "backfill". The computation of the two fronts alternates in the decoding process, resulting in more effective pruning than the standard one-pass decoding with an on-the-fly composition decoder. Experiments show that the proposed decoder works notably faster than the standard one-pass decoding with on-the-fly composition decoder, while the acceleration will be more obvious with the increment of data complexity.

cs.SD↗

arXiv2021

Learning Policies for Multilingual Training of Neural Machine Translation Systems

Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple search based curricula -- orderings of the multilingual training data -- which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally, we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system with the aid of contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.

cs.CL↗

arXiv2021

Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora

Large web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since these corpora are typically extremely noisy, their use is fairly limited. Current approaches to dealing with this problem mainly focus on filtering using heuristics or single features such as language model scores or bi-lingual similarity. This work presents an alternative approach which learns weights for multiple sentence-level features. These feature weights which are optimized directly for the task of improving translation performance, are used to score and filter sentences in the noisy corpora more effectively. We provide results of applying this technique to building NMT systems using the Paracrawl corpus for Estonian-English and show that it beats strong single feature baselines and hand designed combinations. Additionally, we analyze the sensitivity of this method to different types of noise and explore if the learned weights generalize to other language pairs using the Maltese-English Paracrawl corpus.

cs.CL↗

arXiv2021

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition. First, lattices from first-pass decoding are expanded by the proposed posterior-based lattice expansion algorithm. Second, each expanded lattice is converted into a minimal list of hypotheses that covers every arc. Each hypothesis is constrained to be the best path for at least one arc it includes. For each lattice, the neural LM scores of the minimal list are computed in parallel and are then integrated back to the lattice in the rescoring stage. Experiments on the Switchboard dataset show that the proposed rescoring strategy obtains comparable recognition performance and generates more compact lattices than a competitive baseline method. Furthermore, the parallel rescoring method offers more flexibility by simplifying the integration of PyTorch-trained neural LMs for lattice rescoring with Kaldi.

eess.AS↗

arXiv2021

Training Noisy Single-Channel Speech Separation With Noisy Oracle Sources: A Large Gap and A Small Step

As the performance of single-channel speech separation systems has improved, there has been a desire to move to more challenging conditions than the clean, near-field speech that initial systems were developed on. When training deep learning separation models, a need for ground truth leads to training on synthetic mixtures. As such, training in noisy conditions requires either using noise synthetically added to clean speech, preventing the use of in-domain data for a noisy-condition task, or training using mixtures of noisy speech, requiring the network to additionally separate the noise. We demonstrate the relative inseparability of noise and that this noisy speech paradigm leads to significant degradation of system performance. We also propose an SI-SDR-inspired training objective that tries to exploit the inseparability of noise to implicitly partition the signal and discount noise separation errors, enabling the training of better separation systems with noisy oracle sources.

eess.AS↗

arXiv2021

Wake Word Detection with Streaming Transformers

Modern wake word detection systems usually rely on neural networks for acoustic modeling. Transformers has recently shown superior performance over LSTM and convolutional networks in various sequence modeling tasks with their better temporal modeling power. However it is not clear whether this advantage still holds for short-range temporal modeling like wake word detection. Besides, the vanilla Transformer is not directly applicable to the task due to its non-streaming nature and the quadratic time and space complexity. In this paper we explore the performance of several variants of chunk-wise streaming Transformers tailored for wake word detection in a recently proposed LF-MMI system, including looking-ahead to the next chunk, gradient stopping, different positional embedding methods and adding same-layer dependency between chunks. Our experiments on the Mobvoi wake word dataset demonstrate that our proposed Transformer model outperforms the baseline convolution network by 25% on average in false rejection rate at the same false alarm rate with a comparable model size, while still maintaining linear complexity w.r.t. the sequence length.

cs.CL↗

arXiv2021

Frustratingly Easy Noise-aware Training of Acoustic Models

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it requires many-folds data augmentation, resulting in increased training time. In this paper, we propose utterance-level noise vectors for noise-aware training of acoustic models in hybrid ASR. Our noise vectors are obtained by combining the means of speech frames and silence frames in the utterance, where the speech/silence labels may be obtained from a GMM-HMM model trained for ASR alignments, such that no extra computation is required beyond averaging of feature vectors. We show through experiments on AMI and Aurora-4 that this simple adaptation technique can result in 6-7% relative WER improvement. We implement several embedding-based adaptation baselines proposed in literature, and show that our method outperforms them on both the datasets. Finally, we extend our method to the online ASR setting by using frame-level maximum likelihood for the mean estimation.

eess.AS↗

arXiv2021

The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap

This paper provides a detailed description of the Hitachi-JHU system that was submitted to the Third DIHARD Speech Diarization Challenge. The system outputs the ensemble results of the five subsystems: two x-vector-based subsystems, two end-to-end neural diarization-based subsystems, and one hybrid subsystem. We refine each system and all five subsystems become competitive and complementary. After the DOVER-Lap based system combination, it achieved diarization error rates of 11.58 % and 14.09 % in Track 1 full and core, and 16.94 % and 20.01 % in Track 2 full and core, respectively. With their results, we won second place in all the tasks of the challenge.

eess.AS↗

arXiv2020

Fine-grained activity recognition for assembly videos

In this paper we address the task of recognizing assembly actions as a structure (e.g. a piece of furniture or a toy block tower) is built up from a set of primitive objects. Recognizing the full range of assembly actions requires perception at a level of spatial detail that has not been attempted in the action recognition literature to date. We extend the fine-grained activity recognition setting to address the task of assembly action recognition in its full generality by unifying assembly actions and kinematic structures within a single framework. We use this framework to develop a general method for recognizing assembly actions from observation sequences, along with observation features that take advantage of a spatial assembly's special structure. Finally, we evaluate our method empirically on two application-driven data sources: (1) An IKEA furniture-assembly dataset, and (2) A block-building dataset. On the first, our system recognizes assembly actions with an average framewise accuracy of 70% and an average normalized edit distance of 10%. On the second, which requires fine-grained geometric reasoning to distinguish between assemblies, our system attains an average normalized edit distance of 23% -- a relative improvement of 69% over prior work.

cs.CV↗

arXiv2020

Multi-class Spectral Clustering with Overlaps for Speaker Diarization

This paper describes a method for overlap-aware speaker diarization. Given an overlap detector and a speaker embedding extractor, our method performs spectral clustering of segments informed by the output of the overlap detector. This is achieved by transforming the discrete clustering problem into a convex optimization problem which is solved by eigen-decomposition. Thereafter, we discretize the solution by alternatively using singular value decomposition and a modified version of non-maximal suppression which is constrained by the output of the overlap detector. Furthermore, we detail an HMM-DNN based overlap detector which performs frame-level classification and enforces duration constraints through HMM state transitions. Our method achieves a test diarization error rate (DER) of 24.0% on the mixed-headset setting of the AMI meeting corpus, which is a relative improvement of 15.2% over a strong agglomerative hierarchical clustering baseline, and compares favorably with other overlap-aware diarization methods. Further analysis on the LibriCSS data demonstrates the effectiveness of the proposed method in high overlap conditions.

eess.AS↗

arXiv2020

DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs

Several advances have been made recently towards handling overlapping speech for speaker diarization. Since speech and natural language tasks often benefit from ensemble techniques, we propose an algorithm for combining outputs from such diarization systems through majority voting. Our method, DOVER-Lap, is inspired from the recently proposed DOVER algorithm, but is designed to handle overlapping segments in diarization outputs. We also modify the pair-wise incremental label mapping strategy used in DOVER, and propose an approximation algorithm based on weighted k-partite graph matching, which performs this mapping using a global cost tensor. We demonstrate the strength of our method by combining outputs from diverse systems -- clustering-based, region proposal networks, and target-speaker voice activity detection -- on AMI and LibriCSS datasets, where it consistently outperforms the single best system. Additionally, we show that DOVER-Lap can be used for late fusion in multichannel diarization, and compares favorably with early fusion methods like beamforming.

eess.AS↗

arXiv2020

Neural Language Modeling With Implicit Cache Pointers

A cache-inspired approach is proposed for neural language models (LMs) to improve long-range dependency and better predict rare words from long contexts. This approach is a simpler alternative to attention-based pointer mechanism that enables neural LMs to reproduce words from recent history. Without using attention and mixture structure, the method only involves appending extra tokens that represent words in history to the output layer of a neural LM and modifying training supervisions accordingly. A memory-augmentation unit is introduced to learn words that are particularly likely to repeat. We experiment with both recurrent neural network- and Transformer-based LMs. Perplexity evaluation on Penn Treebank and WikiText-2 shows the proposed model outperforms both LSTM and LSTM with attention-based pointer mechanism and is more effective on rare words. N-best rescoring experiments on Switchboard indicate that it benefits both very rare and frequent words. However, it is challenging for the proposed model as well as two other models with attention-based pointer mechanism to obtain good overall WER reductions.

eess.AS↗

arXiv2020

Mixture of Speaker-type PLDAs for Children's Speech Diarization

In diarization, the PLDA is typically used to model an inference structure which assumes the variation in speech segments be induced by various speakers. The speaker variation is then learned from the training data. However, human perception can differentiate speakers by age, gender, among other characteristics. In this paper, we investigate a speaker-type informed model that explicitly captures the known variation of speakers. We explore a mixture of three PLDA models, where each model represents an adult female, male, or child category. The weighting of each model is decided by the prior probability of its respective class, which we study. The evaluation is performed on a subset of the BabyTrain corpus. We examine the expected performance gain using the oracle speaker type labels, which yields an 11.7% DER reduction. We introduce a novel baby vocalization augmentation technique and then compare the mixture model to the single model. Our experimental result shows an effective 0.9% DER reduction obtained by adding vocalizations. We discover empirically that a balanced dataset is important to train the mixture PLDA model, which outperforms the single PLDA by 1.3% using the same training data and achieving a 35.8% DER. The same setup improves over a standard baseline by 2.8% DER.

eess.AS↗