![]() ![]() ![]() Actually, the WER numbers for them are worse than in June. Microsoft and Amazon both improved by about the same amount.We are actually in the middle of a further round of training with a focus on call center conversations.Īs far as the other recognizers are concerned: ![]() Training on this type of data resulted in a further increase in the accuracy of our model. Since the last benchmark, at Voicegain we invested in more training - mainly lectures - conducted over zoom and in a live setting. While the order has remained the same as the last benchmark, three companies - Amazon, Voicegain and Microsoft showed significant improvement. Back then, the results were as follows (from most accurate to the least): Microsoft, then Amazon closely followed by Voicegain, then new Google latest_long and Google Enhanced last. It has been another 6 months since we published our last speech recognition accuracy benchmark. With Voicegain Transcribe, the entire solution can deployed either in a datacenter (on bare-metal) or in a private cloud. At Voicegain, we offer Voicegain Transcribe, an enterprise-ready solution for Meeting AI. If you are looking for such a solution, we can help. Hence for businesses it is extremely critical that such transcripts are stored only in private infrastructure (behind the firewall). It is really important for Enterprise IT to make sure this happens in order to safeguard proprietary and confidential information. But if these transcripts are stored in another Vendor's cloud, it has the potential to expose very proprietary and confidential information of any business to 3rd parties. Now with the power of LLMs, they can now be queried very easily to provide amazing insights. Meeting transcripts in any business is a veritable gold mine of information. Question 9), it did indicate that in its response.Īt Voicegain, we had always been a big proponents of why Voice AI needs to remain on the Edge. And when it do not have adequate information (e.g. For Question 4, it did indicate that it did not want to answer the question. Are employees happy working in the company?ĬhatGPT's responses to the above questions was amazingly and eerily accurate. What is the progress on a key initiative?ĩ. ![]() Which Cloud provider is the Company using?Ĩ. What new products is the Company planning to develop?ħ. What is the team's opinion on Mongodb Atlas vs Google Firestore?Ħ. Did the Company discuss any trade secrets?ĥ. We were able to get answers to the following questionsġ. Then we provided these related documents as context and the user question as a prompt to GPT 3.5 API so that it could generate the answer. During testing, for each user question, we generated embedding of the question and queried the vector database (i.e knowledge-base) to get related/similar embeddings. We stored these embeddings in an open-source Vector database (our knowledge-base). Our team used Open AI Embeddings API to generate embeddings of our daily meeting transcripts that were conducted over a one-month period. However the LLMs take this to a whole different level. Enterprises did not mind using the cloud infrastructure of the vendor to store the transcripts as what this NLU could do seemed pretty harmless. Most meeting AI assistants extract summaries and action items.Įssentially these NLU models - and many of these predate the LLMs - were able to summarize, extract topics, keywords and phrases. E.g, Revenue intelligence products like Gong extract questions and sales blockers in sales conversations. Once the transcript is generated, NLU models offered by the Meeting AI vendor is used to extract insights. With such multi-tenant offerings, transcription and natural language processing takes place on the Vendor cloud. In the past few years, companies have been primarily using multi-tenant Revenue/Sales Intelligence and Meeting AI SaaS offerings to transcribe business conversations and extract insights. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |