Search Results for author:
Found 53 papers, 20 papers with code
Zero-shot Disfluency Detection for Indian Languages
We present a detailed pipeline to synthetically generate disfluent text and create evaluation datasets for four Indian languages: Bengali, Hindi, Malayalam, and Marathi.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Aligning Multilingual Embeddings for Improved Code-switched Natural Language Understanding
Multilingual pretrained models, while effective on monolingual data, need additional training to work well with code-switched text.
Synthesizing Audio for Hindi WordNet
We also develop voices using the existing implementations of the aforementioned systems, and (2) We use these voices to generate sample audios for randomly chosen words; manually evaluate the audio generated, and produce audio for all WordNet words using the winner voice model.
Hindi Wordnet for Language Teaching: Experiences and Lessons Learnt
This aid is based on modern pedagogical axioms and is aligned to the learning objectives of the syllabi of the school education in India.
The Effect of Pretraining on Extractive Summarization for Scientific Documents
Large pretrained models have seen enormous success in extractive summarization tasks.
Gujarati-English Code-Switching Speech Recognition using ensemble prediction of spoken language
An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents.
Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning
Popular benchmarks (e. g., XNLI) used to evaluate cross-lingual language understanding consist of parallel versions of English evaluation sets in multiple target languages created with the help of professional translators.
DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages
Towards the goal of multilingual disfluency correction, we present a high-quality human-annotated DC corpus covering four important Indo-European languages: English, Hindi, German and French.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Accented Speech Recognition With Accent-specific Codebooks
In this work, we propose a novel accent adaptation approach for end-to-end ASR systems using cross-attention with a trainable set of codebooks.
Temporally Aligning Long Audio Interviews with Questions: A Case Study in Multimodal Data Integration
The problem of audio-to-text alignment has seen significant amount of research using complete supervision during training.
Improving RNN-Transducers with Acoustic LookAhead
RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities.
Adversarial Training For Low-Resource Disfluency Correction
Disfluencies commonly occur in conversational speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
DisfluencyFixer: A tool to enhance Language Learning through Speech To Speech Disfluency Correction
Conversational speech often consists of deviations from the speech plan, producing disfluent utterances that affect downstream NLP tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Towards Zero-Shot Code-Switched Speech Recognition
In this work, we seek to build effective code-switched (CS) automatic speech recognition systems (ASR) under the zero-shot setting where no transcribed CS speech data is available for training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training
Training state-of-the-art ASR systems such as RNN-T often has a high associated financial and environmental cost.
DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
In this work we present \dictdis, a lexically constrained NMT system that disambiguates between multiple candidate translations derived from dictionaries.
Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding
Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded.
Investigating Modality Bias in Audio Visual Video Parsing
We focus on the audio-visual video parsing (AVVP) problem that involves detecting audio and visual event labels with temporal boundaries.
Adaptive Discounting of Implicit Language Models in RNN-Transducers
RNN-Transducer (RNN-T) models have become synonymous with streaming end-to-end ASR systems.
Error Correction in ASR using Sequence-to-Sequence Models
Post-editing in Automatic Speech Recognition (ASR) entails automatically correcting common and systematic errors produced by the ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation
To address this problem, we propose DITTO (Data-efficient and faIr Targeted subseT selectiOn) that uses Submodular Mutual Information (SMI) functions as acquisition functions to find the most informative set of utterances matching a target accent within a fixed budget.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning
The original algorithm relies on computationally expensive data augmentation steps that involve perturbing the raw images and computing features for each perturbed image.
Image Augmentation
Semi Supervised Learning for Image Captioning
The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding
In this work, we propose the use of bilingual intermediate pretraining as a reliable technique to derive large and consistent performance gains on three different NLP tasks using code-switched text.
From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text
Generating code-switched text is a problem of growing interest, especially given the scarcity of corpora containing large volumes of real code-switched text.
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights
In this work, we propose the first large scale study of automatic speech recognition (ASR) in Sanskrit, with an emphasis on the impact of unit selection in Sanskrit ASR.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Cross-Modal learning for Audio-Visual Video Parsing
In this paper, we present a novel approach to the audio-visual video parsing (AVVP) task that demarcates events from a video separately for audio and visual modalities.
Ranked #1 on
Event Detection
on Audio Set
Collaborative Learning to Generate Audio-Video Jointly
Towards this, we propose a method that demonstrates that we are able to generate naturalistic samples of video and audio data by the joint correlated generation of audio and video modalities.
Disfluency Correction using Unsupervised and Semi-supervised Learning
Spoken language is different from the written language in its style and structure.
Multilingual and code-switching ASR challenges for low resource Indian languages
For this purpose, we provide a total of ~600 hours of transcribed speech data, comprising train and test sets, in these languages including two code-switched language pairs, Hindi-English and Bengali-English.
Rudder: A Cross Lingual Video and Text Retrieval Dataset
Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input.
Ranked #1 on
Video Retrieval
on Charades-STA
Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering
In response, we identify a key structural idiom in OKVQA , viz., S3 (select, substitute and search), and build a new data set and challenge around it.
Error-driven Fixed-Budget ASR Personalization for Accented Speakers
We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker-specific utterances.
An Investigation of End-to-End Models for Robust Speech Recognition
A systematic comparison of these two approaches for end-to-end robust ASR has not been attempted before.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Meta-Learning for Effective Multi-task and Multilingual Modelling
We present experiments on five different tasks and six different languages from the XTREME multilingual benchmark dataset.
Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages
This work presents a seemingly simple but effective technique to improve low-resource ASR systems for phonetic languages.
Improving Low Resource Code-switched ASR using Augmented Code-switched TTS
Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems
We use a state-of-the-art end-to-end ASR system, comprising convolutional and recurrent layers, that is trained on a large amount of US-accented English speech and evaluate the model on speech samples from seven different English accents.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020
We also make use of additional fluent text in the target language to help generate fluent translations.
Black-box Adaptation of ASR for Accented Speech
Accordingly, we propose a novel coupling of an open-source accent-tuned local model with the black-box service where the output from the service guides frame-level inference in the local model.
Coupled Training of Sequence-to-Sequence Models for Accented Speech Recognition
We propose coupled training for encoder-decoder ASR models that acts on pairs of utterances corresponding to the same text spoken by speakers with different accents.
Stem-driven Language Models for Morphologically Rich Languages
Neural language models (LMs) have shown to benefit significantly from enhancing word vectors with subword-level information, especially for morphologically rich languages.
End-to-End ASR for Code-switched Hindi-English Speech
While the lack of data adversely affects the performance of end-to-end models, we see promising improvements with MTL and balancing the corpus.
Cross-Lingual Training for Automatic Question Generation
For a new language, such training instances are hard to obtain making the QG problem even more challenging.
Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
This work focuses on building language models (LMs) for code-switched text.
Revisiting the Importance of Encoding Logic Rules in Sentiment Classification
We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences.
Generalizing Across Domains via Cross-Gradient Training
We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains.
Ranked #83 on
Domain Generalization
on PACS
POLICY DRIVEN GENERATIVE ADVERSARIAL NETWORKS FOR ACCENTED SPEECH GENERATION
In this paper, we propose the generation of accented speech using generative adversarial networks.
Leveraging Native Language Speech for Accent Identification using Deep Siamese Networks
The problem of automatic accent identification is important for several applications like speaker profiling and recognition as well as for improving speech recognition systems.
Dual Language Models for Code Switched Speech Recognition
Since code-switching is a blend of two or more different languages, a standard bilingual language model can be improved upon by using structures of the monolingual language models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints
Mismatched transcriptions have been proposed as a mean to acquire probabilistic transcriptions from non-native speakers of a language. Prior work has demonstrated the value of these transcriptions by successfully adapting cross-lingual ASR systems for different tar-get languages.
Clustering-based Phonetic Projection in Mismatched Crowdsourcing Channels for Low-resourced ASR
We evaluate our techniques using mismatched transcriptions for Cantonese speech acquired from native English and Mandarin speakers.
