Introduction This document describes how to configure Cisco UCCE with Nuance Text To Speech (TTS) and Automatic Speech Recognition (ASR). Prerequisites Requirements Cisco recommends that you have knowledge of these topics:. UCCE with Customer Voice Portal (CVP). Cisco Virtualized Voice Browser (CVVB) or Voice Xtended Markup Language (VXML) Gateway. Nuance TTS and ASR Server Components Used The information in this document is based on these software versions:. CVP 11.6. UCCE 11.6.
VVB 11.6. Nuance Recognizer 10.0. Nuance Speech Server 6.2.x The information in this document was created from the devices in a specific lab environment.
All of the devices used in this document started with a cleared (default) configuration. If your network is live, ensure that you understand the potential impact of any command. Basic Configuration Cisco UCCE Configuration on VVB Step 1. Log in to CVVB Administration page: Step 2. Navigate to SubSystem Speech Servers TTS Servers. Configure the TTS server as shown in the image.
Vocalizer TTS Voice (English) - Vocalizer is an embedded TTS engine that provides expressive and natural sounding voices in over 50 languages: US English,. Prompts using text-to-speech. (TTS) technology. By providing your developers with a single source for all audio output, Vocalizer gracefully combines computer-.
Note: 192.168.33.28 is TTS server Internet Protocol (IP) Address. If the use of a machine name, instead of IP address, is required in your deployment, in the Server Name field, provide the machine name instead of the IP address. In that case, you need to reference the machine IP address in the ect/hosts file. This command on VVB Command Line Interface (CLI) makes the link between name and IP address in etc/hosts: utils VVB add host-to-ip Example: utils VVB add host-to-ip nuance 192.168.33.28 Configuration on VXML GW (If VVB is not deployed) Step 1.
Define Hostname to IP address mapping for ASR and TTS servers. Ip host asr - en -us 192.168.33.28 ip host tts - en -us 192.168.33.28 i p host tts-fr-fr 192.168.33.28 i p host asr-fr-fr 192.168.33.28 i p host tts -de-de 192.168.33.28 ip host asr -de-de 192.168.33.28 ip host tts-pt-pt 192.168.33.28 Ip host asr-pt-pt 192.168.33.28 ip host IPCC-Nuance 192.168.33.28 Step 2. Define the Voice class Uniform Resource Identifier (URI) to match the Session Initiation Protocol (SIP) URI of ASR Server in the dial-peer.
Voice class uri ASR sip pattern [email protected] Step 3. Define the Voice class URI to match the SIP URI of TTS Server in the dial-peer. Voice class uri TTS sip pattern Step 4. Define the amount of maximum memory to used for downloaded prompts. Ivr prompt memory 15000 Step 5. Define the SIP URI of ASR and TTS Server. Ivr asr -server sip:[email protected] ivr tts -server Step 6.
Configure the SIP Voice Over IP (VOIP) dial-peers. These dial-peers are used as an outbound dial-peer when the gateway initiates a Media Resource Control Protocol (MRCP) over SIP session to the ASR/TTS server (MRCP Version 2). Dial-peer voice 5 voip description Dial-peer for ARS Nuance session protocol sipv2 session target ipv4:192.168.33.28 session transport tcp destination uri ASR dtmf -relay rtp-nte codec g711ulaw no vad! Dial-peer voice 6 voip description Dial-peer for TTS Nuance session protocol sipv2 session target ipv4:192.168.33.28 session transport tcp destination uri TTS dtmf -relay rtp-nte codec g711ulaw no vad Text To Speech on CVP Call Studio The TTS server is called when an audio element in CVP Call Studio is not configured or the audio file does not exist in the specified URI and default audio path.
Select the audio element. Select the Audio tab, and navigate to audio item. Configure the audio item in order to use text to speech instead of audo files.
Write the text you want to convert to speech in the TTS field, as shown in the image. Multi-Languages support The Application Modifier element in CVP Call Studio allows to provide multi-languange suppport.
Here is an example of script that uses different languages. Note: You are required to install the langage pack you support, in the Nuance TTS/ASR server. For example, to use German (de-DE), a German language pack on the TTS server is required.
Configure Multi-Languages Step 1. In order to select the language, set the language field in the application modifier element, as shown in the image. Now, the German(de-DE) language pack is used in the next audio element. To revert back to another language, use the application modifier once again. Note: To use Cisco VVB with multi-languages, it is required to install the following Engineering Specials (ES): 11.5ES43 and 11.6 ES22. More information on. Basic Configuration Nuance ASR/TTS server After you have installed Nuance ASR/TTS server and the license is configured, there are few more tasks you need to do, in order to complete the configuration with UCCE.
Speech Server Configuration Step 1. Open the file: C: Program Files (x86) Nuance Speech Server Server config NSSserver.cfg. Search for server.mrcp1.resource.2.url and change the value to /synthesizer from media /speechsynthesizer. Search for server.mrcp1.resource.3.url and change the value to /recognizer from media/speechrecognizer.
Search for server.mrcp1.osrspeechrecog.cache.maxNumber and set the variable value to the number of recognizer licenses you have. For instance, If you have 4 ports license then change the variable value to 4.
Step 5.Search for server.mrcp1.osrspeechrecog.startOfSpeechOnDTM and set the variable value to 0(zero) from 1. Recognizer Configuration Step 1. Open the file: C: Program Files Nuance Recognizer config Baseline.xml.
Set the param values to maximum number of recognizer licenses from default value. 0 4 0 4 Note: Here the value 4 has been specified, since this is a 4-port Nuance license implementation. Vocalizer Configuration Step 1. Open the file: C: Program Files (x86) Nuance Vocalizer for Enterprise config Baseline.xml. Set the param values to maximum number of synthesizer licenses. 4 4 4 Step 3.
Modify ssmlvalidation from strict to warn.
Contents. General Name Creator(s) First public release date Latest stable version Cost Alfanum 2004 2018? 1984 2007, October 26 Bundled with Bundled? 2008 $295 – $995 Cepstral 2000 2013 $29+ CereProc 2006 2017, February £25.99+ CPqD 1999 2016, March 1st? Jonathan Duddington 2006, February 10 2014, April 6 Free Cameron Wong 2008, March 26 2013, January 15 Free Voxygen SAS 2011, September? 2014, December Free Paul Lamere Philip Kwok Dirk Schnelle-Walka Willie Walker. 2001, December 14 2009, March 9 Free 2006, March 2016, December €29 – €885 IVONA Software 2005?
Free for Android 1975 2011? 1995 2009 Bundled with Bundled 2002 2013? Nuance Communications, Inc.?
2013 Not Free Paul Boersma David Weenink? 2016, December 12 Free Nuance Communications, Inc.??? Technical voice details Platform WS Yes 4.x/5.x??? Yes 5.x Yes Yes Yes Yes 5.x Yes Yes Yes Yes Yes Yes 1.0/1.1 5.1 /5.3 Yes 1.0 Yes Yes 5.x Yes Yes Yes Yes Yes Yes 4.x/5.x Yes 5.x 1.0/1.1 5.x? Technical details Name Online demo Available language(s) Available voices Programming language Alfanum TTS Yes Serbian, Croatian 8 C? English (United States). Yes English (British), English (Indian), English (US), French, French (Canadian), German, Italian, Spanish (Latin American) 20 C Yes English (British), English (US), Italian, French (Canadian), German, Spanish (American).
This section's use of may not follow Wikipedia's policies or guidelines. Please by removing or external links, and converting useful links where appropriate into. ( January 2019) Name Creator(s) Available languages (voices) Latest version Last updated Google Play Store rating Voxygen - Expressive Speech Voxygen 6 (50) 1.6.0 2017-12 varies (4-5) Acapela TTS Voices Acapela Group 35 (100+) 4.0.0.6 2015-04-07 3.6 (2,111) CereProc Text-to-Speech CereProc 11 (26) 4.0.5 2017-03 varies Eloquence Text-To-Speech Nuance 10 1.2.0 2015-03-02 4.3 (129) eSpeak eSpeak 40+ 1.-12-14 3.3 (1,762) Google TTS Google 13 (16)? 2015-04-07 4.0 (429,325) IVONA Text-to-Speech HQ IVONA 13 (13) 1.6.42.524 2015-06-23 3.9 (14,413) NeoSpeech NewsSpeak NeoSpeech 1 (7) 1.1.0 2014-12-30 4.8 (16) SVOX Classic Text-to-Speech Nuance 25+ (40+)? 2012-09-28 3.7 (15,740) Vocalizer Nuance 36 (80+) 1.0.5 2015-04-23 3.5 (487).
Comments are closed.
|
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |