Automatic call section segmentation for contact-center calls

Park, Youngja

doi:10.1145/1321440.1321459

Cited by 14 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that in these approaches we assume utterances as basic units instead of the words. To convert the word sequence in the transcript into utterances we use utterance boundary detection algorithm described in [14]. The method is tuned to generate short utterances such that an utterance is unlikely to span two or more topics.…”

Section: Topic Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Call transcript segmentation using word cooccurrence model

Ikbal

Visweswariah

2010

2010 IEEE Spoken Language Technology Workshop

View full text Add to dashboard Cite

In this paper, we propose a word cooccurrence model to perform topic segmentation of call center conversational speech. This model is estimated from training data to discriminatively represent how likely various pairs of words are to cooccur within homogeneous topic segments. We show that such model provide an effective measure of lexical cohesion and hence provide useful evidence of topical coherence or lack thereof between various parts of the call transcripts. We propose two approaches of utilizing such evidence for segmentation: 1) An efficient dynamic programming algorithm to perform segmentation simply utilizing the word cooccurrence model. 2) Extracting features based on word cooccurrence model to utilize them as additional features in conditional random field (CRF) based segmentation. Experimental evaluation of these approaches against state-of-the-art approaches show the effectiveness of word cooccurrence model for the topic segmentation task.Index Terms-topic segmentation, word cooccurrence, dynamic programming algorithm, conditional random field, complementary features.

show abstract

Section: Topic Segmentationmentioning

confidence: 99%

“…The data set used (same as in [14]) for experimental evaluation consists of automatic speech recognition transcripts of 100 calls that are conversations between agents and customers in a help-desk scenario. This data set comprises 13.2 hours of calls consisting of 5350 utterances.…”

Section: Databasementioning

confidence: 99%

Call transcript segmentation using word cooccurrence model

Ikbal

Visweswariah

2010

2010 IEEE Spoken Language Technology Workshop

View full text Add to dashboard Cite

show abstract

“…Domain-specific words and acronyms are rendered with the expected capitalization patterns (e.g., "ABS"), as is the pronoun "I." Sentence boundaries are detected, using the methods described in [10], and the resulting sentences are given initial capitals and punctuated with periods.…”

Section: Token and Sentence Normalizationmentioning

confidence: 99%

“…An utterance boundary detector [10] divides the continuous stream of words from the recognition engine into normal sentences. The algorithm, based on Maximum Entropy classification, uses linguistic and prosodic features such as the probabilities of unigrams and bi-grams occurring as the first or last unigram (or bi-gram) in utterances, and the length of pauses between two words.…”

Section: Sentence and Segment Boundary Detectionmentioning

confidence: 99%

Semi-automated logging of contact center telephone calls

Byrd

Neff

Teiken

et al. 2008

Proceedings of the 17th ACM Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Modern businesses use contact centers as a communication channel with users of their products and services. The largest factor in the expense of running a telephone contact center is the labor cost of its agents. IBM Research has built a new system, Contact-Center Agent Buddies (CAB), which is designed to help reduce the average handle time (AHT) for customer calls, thereby also reducing their cost. In this paper, we focus on the call logging subsystem, which helps agents reduce the time they spend documenting those calls. We built a Template CAB and a Call Logging CAB, using a pipeline consisting of audio capture of a telephone conversation, automatic speech recognition, text analysis, and log generation. We developed techniques for ASR text cleansing, including normalization of expressions and acronyms, domain terms, capitalization, and boundaries for sentences, paragraphs, and call segments. We found that simple heuristics suffice to generate high-quality logs from the normalized sentences. The pipeline yields a candidate call log which the agents can edit in less time than it takes them to generate call logs manually. Evaluation of the Call Logging CAB in an industrial contact center environment shows that it reduces the amount of time agents spend logging calls by at least 50% without compromising the quality of the resulting call documentation.

show abstract

“…In such a scenario, summarization would play the role of a feature selection module to choose essential intent conveying part useful for further processing, discarding the irrelevant parts. A similar approach of using shorter segments of the conversations has been shown to be beneficial in a call classification task [4] where simply the initial part of the conversation is used. However, it still used large initial parts of the conversations assuming the relevant part is captured there.…”

Section: Introductionmentioning

confidence: 99%

Intent focused summarization of caller-agent conversations

Ikbal

Verma

Ghosh

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

In this paper, we propose a conditional random field (CRF) based approach to identify segments within call center conversations that convey caller intent. A distinguishing aspect of our approach is the use of context information of the intent bearing segments to predict the presence or absence of intents within various segments. The context is represented through a set of phrase features that are frequently present in and around the intent bearing segments. These phrases, identified in a data-driven manner, are used along with conventional word features in a CRF based sequence labeling framework to assign intent/non-intent labels to each utterance in a conversation. Another distinguishing aspect of our approach is that instead of using 1-best label alignment, we extract N-best label alignments at the output of CRF and combine evidences from them to rank the utterances according to their intent bearing potential, so that top ranked utterances can be chosen as the intent summary. To demonstrate the effectiveness of our approach and to evaluate the influence of automatic speech recognition (ASR) errors we evaluated our approach using manually transcribed and ASR transcribed conversations. Experimental results show improved summarization accuracy using our approach. Specifically, in 92% of the manually transcribed conversations accurate summaries of just one utterance length can be extracted using the proposed approach.

show abstract

Automatic call section segmentation for contact-center calls

Cited by 14 publications

References 16 publications

Call transcript segmentation using word cooccurrence model

Call transcript segmentation using word cooccurrence model

Semi-automated logging of contact center telephone calls

Intent focused summarization of caller-agent conversations

Contact Info

Product

Resources

About