Zeeshan Ahmed


pdf bib
PersonaLM: Language Model Personalization via Domain-distributed Span Aggregated K-Nearest N-gram Retrieval Augmentation
Puneet Mathur | Zhe Liu | Ke Li | Yingyi Ma | Gil Keren | Zeeshan Ahmed | Dinesh Manocha | Xuedong Zhang
Findings of the Association for Computational Linguistics: EMNLP 2023

We introduce PersonaLM - Domain-distributed Span-Aggregated K-nearest N-gram retrieval augmentation to improve language modeling for Automatic Speech Recognition (ASR) personalization. PersonaLM leverages contextually similar n-gram word frequencies for recognizing rare word patterns associated with unseen domains. It aggregates the next-word probability distribution based on the relative importance of different domains to the input query. To achieve this, we propose a Span Aggregated Group-Contrastive Neural (SCAN) retriever that learns to rank external domains/users by utilizing a group-wise contrastive span loss that pulls together span representations belonging to the same group while pushing away spans from unrelated groups in the semantic space. We propose ASAP benchmark for ASR LM personalization that consists of three user-specific speech-to-text tasks for meetings, TED talks, and financial earnings calls. Extensive experiments show that PersonaLM significantly outperforms strong baselines with a 10-16% improvement in perplexity and a 5-8% reduction in Word Error Rates on popular Wikitext-103, UserLibri, and our ASAP dataset. We further demonstrate the usefulness of the SCAN retriever for improving user-personalized text generation and classification by retrieving relevant context for zero-shot prompting and few-shot fine-tuning of LLMs by 7-12% on the LAMP benchmark.


pdf bib
CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals
Scott Novotney | Sreeparna Mukherjee | Zeeshan Ahmed | Andreas Stolcke
Findings of the Association for Computational Linguistics: ACL 2022

We propose a framework to modularize the training of neural language models that use diverse forms of context by eliminating the need to jointly train context and within-sentence encoders. Our approach, contextual universal embeddings (CUE), trains LMs on one type of contextual data and adapts to novel context types. The model consists of a pretrained neural sentence LM, a BERT-based contextual encoder, and a masked transfomer decoder that estimates LM probabilities using sentence-internal and contextual evidence. When contextually annotated data is unavailable, our model learns to combine contextual and sentence-internal information using noisy oracle unigram embeddings as a proxy. Real context data can be introduced later and used to adapt a small number of parameters that map contextual data into the decoder’s embedding space. We validate the CUE framework on a NYTimes text corpus with multiple metadata types, for which the LM perplexity can be lowered from 36.6 to 27.4 by conditioning on context. Bootstrapping a contextual LM with only a subset of the metadata during training retains 85% of the achievable gain. Training the model initially with proxy context retains 67% of the perplexity gain after adapting to real context. Furthermore, we can swap one type of pretrained sentence LM for another without retraining the context encoders, by only adapting the decoder model. Overall, we obtain a modular framework that allows incremental, scalable training of context-enhanced LMs.


pdf bib
WinkTalk: a demonstration of a multimodal speech synthesis platform linking facial expressions to expressive synthetic voices
Éva Székely | Zeeshan Ahmed | João P. Cabral | Julie Carson-Berndsen
Proceedings of the Third Workshop on Speech and Language Processing for Assistive Technologies

pdf bib
Rapidly Testing the Interaction Model of a Pronunciation Training System via Wizard-of-Oz
Joao Paulo Cabral | Mark Kane | Zeeshan Ahmed | Mohamed Abou-Zleikha | Éva Székely | Amalia Zahra | Kalu Ogbureke | Peter Cahill | Julie Carson-Berndsen | Stephan Schlögl
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

This paper describes a prototype of a computer-assisted pronunciation training system called MySpeech. The interface of the MySpeech system is web-based and it currently enables users to practice pronunciation by listening to speech spoken by native speakers and tuning their speech production to correct any mispronunciations detected by the system. This practice exercise is facilitated in different topics and difficulty levels. An experiment was conducted in this work that combines the MySpeech service with the WebWOZ Wizard-of-Oz platform (http://www.webwoz.com), in order to improve the human-computer interaction (HCI) of the service and the feedback that it provides to the user. The employed Wizard-of-Oz method enables a human (who acts as a wizard) to give feedback to the practising user, while the user is not aware that there is another person involved in the communication. This experiment permitted to quickly test an HCI model before its implementation on the MySpeech system. It also allowed to collect input data from the wizard that can be used to improve the proposed model. Another outcome of the experiment was the preliminary evaluation of the pronunciation learning service in terms of user satisfaction, which would be difficult to conduct before integrating the HCI part.

pdf bib
Hierarchical Phrase-Based MT for Phonetic Representation-Based Speech Translation
Zeeshan Ahmed | Jie Jiang | Julie Carson-Berndsen | Peter Cahill | Andy Way
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers

The paper presents a novel technique for speech translation using hierarchical phrased-based statistical machine translation (HPB-SMT). The system is based on translation of speech from phone sequences as opposed to conventional approach of speech translation from word sequences. The technique facilitates speech translation by allowing a machine translation (MT) system to access to phonetic information. This enables the MT system to act as both a word recognition and a translation component. This results in better performance than conventional speech translation approaches by recovering from recognition error with help of a source language model, translation model and target language model. For this purpose, the MT translation models are adopted to work on source language phones using a grapheme-to-phoneme component. The source-side phonetic confusions are handled using a confusion network. The result on IWLST'10 English- Chinese translation task shows a significant improvement in translation quality. In this paper, results for HPB-SMT are compared with previously published results of phrase-based statistical machine translation (PB-SMT) system (Baseline). The HPB-SMT system outperforms PB-SMT in this regard.


pdf bib
Phonetic Representation-Based Speech Translation
Jie Jiang | Zeeshan Ahmed | Julie Carson-Berndsen | Peter Cahill | Andy Way
Proceedings of Machine Translation Summit XIII: Papers