B. Pellom

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by B. Pellom

Growing an n-gram language model

Interspeech 2005

Traditionally, when building an n-gram model, we decide the span of the model history, collect th... more Traditionally, when building an n-gram model, we decide the span of the model history, collect the relevant statistics and estimate the model. The model can be pruned down to a smaller size by manipulating the statistics or the estimated model. This paper shows how an n-gram model can be built by adding suitable sets of n-grams to a unigram model until desired complexity is reached. Very high order n-grams can be used in the model, since the need for handling the full unpruned model is eliminated by the proposed technique. We compare our growing method to entropy based pruning. In Finnish speech recognition tests, the models trained by the growing method outperform the entropy pruned models of similar size.

Download

Call-type classification and unsupervised training for the call center domain

2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721), 2003

In this paper we describe recent experiments in call-type classification and acoustic modeling fo... more In this paper we describe recent experiments in call-type classification and acoustic modeling for speech recognition in the call center domain. We first describe the CU Call Center Corpus, a database of human-to-human conversations recorded from an Information Technology (IT) Help Desk call center located on the University of Colorado campus. Next, we describe our analysis and labeling of the recorded conversations into a hierarchical taxonomy of the call types. We consider four methods for call-type classification and provide initial experiments illustrating classification error rates for this new task domain. It is shown that lightly supervised training based on using the output from an automatic speech recognizer in conjunction with supervised labeling of calls by call-type can substantially reduce classification error rates and development efforts when only limited training data are available. A call-type classification error rate of 24% is achieved using a classifier based on Support Vector machines. Finally, we consider issues related to unsupervised acoustic and language model training for improved call transcription and point to directions for future work.

Download

1.1 Overview

This paper presents recent improvements in the development of the University of Colorado “CU Comm... more This paper presents recent improvements in the development of the University of Colorado “CU Communicator ” and “CU-Move ” spoken dialog systems. First, we describe the CU Communicator system that integrates speech recognition, synthesis and natural language understanding technologies using the DARPA Hub Architecture. Users are able to converse with an automated travel agent over the phone to retrieve up-to-date travel information such as flight schedules, pricing, along with hotel and rental car availability. The CU Communicator has been under development since April of 1999 and represents our test-bed system for developing robust human-computer interactions where reusability and dialogue system portability serve as two main goals of our work. Next, we describe our more recent work on the CU Move dialog system for in-vehicle route planning and guidance. This work is in joint collaboration with HRL and is sponsored as part of the DARPA Communicator program. Specifically, we will pro...

The Use of Metalinguistic Knowledge in a Polish Literacy Tutor

Word splitting for Turkish LVCSR

Confidence Measures for Dialogue Systems

International Conference on Acoustics, Speech, and Signal Processing, 2001

A distributed architecture for robust automatic speech recognition

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)., 2003

... m: Word graph, possibly model marked, with acoustic and language model scores from the rescor... more

An Improved Constrained Iterative Speech Enhancement Algorithm for Colored Noise Environments

Turkish speech corpora and recognition tools developed by porting SONIC: Towards multilingual speech recognition

Computer Speech & Language, 2007

This paper presents work on developing speech corpora and recognition tools for Turkish by portin... more This paper presents work on developing speech corpora and recognition tools for Turkish by porting SONIC, a speech recognition tool developed initially for English at the Center for Spoken Language Research of the University of Colorado at Boulder. The work presented in this paper had two objectives: The first one is to collect a standard phonetically-balanced Turkish microphone speech corpus

The Cu Communicator SYSTEM1

... are to templates to output the value of the field in various languages, some formal, and some... more

Italian literacy tutor-tools and technologies for individuals with cognitive disabilities

Italian Children's Speech Recognition with Application to Interactive Books and Tutors

istc.cnr.it

... These have included French, German, Spanish, Portuguese, Russian, Arabic, Korean, Japanese an... more

Statistical Machine Translation Framework for Modeling Phonological Errors in Computer Assisted Pronunciation Training System

Sonic: The university of colorado continuous speech recognizer

Improvements in audio processing and language modeling in the CU Communicator

This paper presents some up-to-date audio processing techniques which have been developed and int... more This paper presents some up-to-date audio processing techniques which have been developed and integrated into the University of Colorado (CU) communicator system. The CU Communicator is an interactive human-machine dialogue system for airline, hotel and rental car information. The baseline system was fully functional in June 1999. Since then, many improvements have been made. The paper will concentrate on acoustic echo cancellation, voice activity detection (VAD) and language modeling techniques and provide a paradigm for speech and audio processing in a dialog system with barge-in capabilities. Specifically, a real-time block least-mean-square (LMS) algorithm is discussed. A robust voice activity detector using energy threshold is applied to detect user voice. Experimental results are presented and some real-time implementation issues are addressed.

Download

Robust digit recognition in noise: an evaluation using the AURORA Corpus

by Umit Yapanel and B. Pellom

In this paper, a variety of techniques for robust digit recognition in noise are considered using... more In this paper, a variety of techniques for robust digit recognition in noise are considered using the AURORA 2.0 corpus. Current recognizers perform as well as humans in small vocabulary tasks but computer recognition performance degrades substantially when noise is introduced into the speech, while human performance is much less sensitive. To make the recognizer robust, several methodologies are employed. These include, feature processing, enhancement before recognition and model adaptation. We considered a number of processing and adaptation scenarios depending on noise type. The best performance, as expected, was obtained in matched training conditions which in general has limited applicability in real world problems. As a feature processing step, using RCCs (Root Cepstrum Coeff.) instead of MFCCs gave substantial improvement. MFCC with front-end enhancement increased performance considerably, but results were far from that obtained with matched training. When we combine the RCC with enhancement, however, we get the best results. In the next step, we employed model adaptation techniques which outperformed MFCC+enhancement and gave much closer results to the matched condition limits. However, MFCC adaptation could not outperform RCC parameterization with front-end enhancement, which we show is much more computationally efficient than model adaptation.

Download

Robust speech recognition in noise: an evaluation using the SPINE corpus

by Umit Yapanel and B. Pellom

In this paper, methodologies for effective speech recognition are considered along with evaluatio... more In this paper, methodologies for effective speech recognition are considered along with evaluations of an NRL speech in noise corpus entitled SPINE. When speech is produced in adverse conditions that include high levels of noise, workload task stress, and Lombard effect, new challenges arise concerning how to best improve recognition performance. Here, we consider tradeoffs in (i) robust features, (ii) front-end noise suppression, (iii) model adaptation, and (iv) training and testing in the same conditions. The type of noise and recording conditions can significantly impact the type of signal processing and speech modeling methods that would be most effective in achieving robust speech recognition. We considered alternative frequency scales (M-MFCC, ExpoLog), feature processing (CMN, VCMN, LP-vs-FFT MFCCs), model adaptation (PMC), and combinations of gender dependent with gender independent models. For the purposes of achieving effective speech recognition performance, computational speed and availability of adaptation data greatly impacts final recognition performance. In particular, while reliable algorithm formulations for addressing specific types of distortion can improve recognition rates, these algorithms cannot reach their full potential without proper front-end algorithm data processing to direct compensation. While parallel banks of speech recognizers can improve recognition performance, their significant computational requirements can render the recognizer useless in actual speech applications.

Download

Speech Systems for Route Navigation

by Umit Yapanel and B. Pellom

CU-Move: Advanced In-Vehicle Speech Systems for Route Navigation

by Umit Yapanel and B. Pellom

DSP for In-Vehicle and Mobile Systems, 2005

In this chapter, we present our recent advances in the formulation and development of an in-vehic... more In this chapter, we present our recent advances in the formulation and development of an in-vehicle hands-free route navigation system. The system is comprised of a multi-microphone array processing front-end, environmental sniffer (for noise analysis), robust speech recognition system, and dialog manager and information servers. We also present our recently completed speech corpus for in-vehicle interactive speech systems for route planning and navigation. The corpus consists of five domains which include: digit strings, route navigation expressions, street and location sentences, phonetically balanced sentences, and a route navigation dialog in a human Wizard-of-Oz like scenario. A total of 500 speakers were collected from across the United States of America during a six month period from April-Sept. 2001. While previous attempts at in-vehicle speech systems have generally focused on isolated command words to set radio frequencies, temperature control, etc., the CU-Move system is focused on natural conversational interaction between the user and in-vehicle system. After presenting our proposed in-vehicle speech system, we consider advances in multi-channel array processing, environmental noise speaker normalization for robust ASR, and our back-end dialog navigation information retrieval sub-system connected to the WWW. Results are presented in each sub-section with a discussion at the end of the chapter.

Download

Robust Speech Processing for In-Vehicle Voice Navigation Systems

by Umit Yapanel and B. Pellom

... John HL Hansen, Murat Akbacak, Umit Yapanel, Xianxian Zhang, Bryan Pellom, Wayne Ward Center ... more

B. Pellom

Uploads

Papers by B. Pellom

Log In